Upload folder using huggingface_hub
Browse files
.summary/0/events.out.tfevents.1731412340.kemove-z690-a
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:145f1c12a06c25649530c66124d27324d8c09f0405ac69ecf28fdee8af82e893
|
| 3 |
+
size 233544
|
README.md
CHANGED
|
@@ -15,7 +15,7 @@ model-index:
|
|
| 15 |
type: doom_health_gathering_supreme
|
| 16 |
metrics:
|
| 17 |
- type: mean_reward
|
| 18 |
-
value:
|
| 19 |
name: mean_reward
|
| 20 |
verified: false
|
| 21 |
---
|
|
@@ -38,19 +38,19 @@ python -m sample_factory.huggingface.load_from_hub -r sun-s/rl_course_vizdoom_he
|
|
| 38 |
|
| 39 |
To run the model after download, use the `enjoy` script corresponding to this environment:
|
| 40 |
```
|
| 41 |
-
python -m .
|
| 42 |
```
|
| 43 |
|
| 44 |
|
| 45 |
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
|
| 46 |
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
|
| 47 |
-
|
| 48 |
## Training with this model
|
| 49 |
|
| 50 |
To continue training with this model, use the `train` script corresponding to this environment:
|
| 51 |
```
|
| 52 |
-
python -m .
|
| 53 |
```
|
| 54 |
|
| 55 |
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
| 56 |
-
|
|
|
|
| 15 |
type: doom_health_gathering_supreme
|
| 16 |
metrics:
|
| 17 |
- type: mean_reward
|
| 18 |
+
value: 12.95 +/- 5.64
|
| 19 |
name: mean_reward
|
| 20 |
verified: false
|
| 21 |
---
|
|
|
|
| 38 |
|
| 39 |
To run the model after download, use the `enjoy` script corresponding to this environment:
|
| 40 |
```
|
| 41 |
+
python -m <path.to.enjoy.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
|
| 42 |
```
|
| 43 |
|
| 44 |
|
| 45 |
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
|
| 46 |
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
|
| 47 |
+
|
| 48 |
## Training with this model
|
| 49 |
|
| 50 |
To continue training with this model, use the `train` script corresponding to this environment:
|
| 51 |
```
|
| 52 |
+
python -m <path.to.train.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
|
| 53 |
```
|
| 54 |
|
| 55 |
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
| 56 |
+
|
checkpoint_p0/best_000001490_6103040_reward_28.179.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2614aaf0814d0a444edf755afc63d5195a9058dc33a69080721d79d2062dd236
|
| 3 |
+
size 34929051
|
checkpoint_p0/checkpoint_000001758_7200768.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:010ebfe2409062777380df8938dfb9d26eae4682b410c02c077802370e2340b0
|
| 3 |
+
size 34929541
|
checkpoint_p0/checkpoint_000001955_8007680.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:feaf3e49930218238ee82fdb03e6bbb6d501e4e620c9989b9ac338d8aafc2bef
|
| 3 |
+
size 34929541
|
config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"algo": "APPO",
|
| 4 |
"env": "doom_health_gathering_supreme",
|
| 5 |
"experiment": "default_experiment",
|
| 6 |
-
"train_dir": "/
|
| 7 |
"restart_behavior": "resume",
|
| 8 |
"device": "gpu",
|
| 9 |
"seed": null,
|
|
@@ -46,6 +46,8 @@
|
|
| 46 |
"learning_rate": 0.0001,
|
| 47 |
"lr_schedule": "constant",
|
| 48 |
"lr_schedule_kl_threshold": 0.008,
|
|
|
|
|
|
|
| 49 |
"obs_subtract_mean": 0.0,
|
| 50 |
"obs_scale": 255.0,
|
| 51 |
"normalize_input": true,
|
|
@@ -128,14 +130,13 @@
|
|
| 128 |
"wide_aspect_ratio": false,
|
| 129 |
"eval_env_frameskip": 1,
|
| 130 |
"fps": 35,
|
| 131 |
-
"command_line": "--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=
|
| 132 |
"cli_args": {
|
| 133 |
"env": "doom_health_gathering_supreme",
|
| 134 |
"num_workers": 8,
|
| 135 |
"num_envs_per_worker": 4,
|
| 136 |
-
"train_for_env_steps":
|
| 137 |
},
|
| 138 |
"git_hash": "unknown",
|
| 139 |
-
"git_repo_name": "not a git repository"
|
| 140 |
-
"train_script": ".usr.local.lib.python3.10.dist-packages.colab_kernel_launcher"
|
| 141 |
}
|
|
|
|
| 3 |
"algo": "APPO",
|
| 4 |
"env": "doom_health_gathering_supreme",
|
| 5 |
"experiment": "default_experiment",
|
| 6 |
+
"train_dir": "/media/kemove/17a64fef-179c-4620-a965-511df0584b38/home/yunpeng/transformers/deep-rl-class-main/notebooks/unit8/train_dir",
|
| 7 |
"restart_behavior": "resume",
|
| 8 |
"device": "gpu",
|
| 9 |
"seed": null,
|
|
|
|
| 46 |
"learning_rate": 0.0001,
|
| 47 |
"lr_schedule": "constant",
|
| 48 |
"lr_schedule_kl_threshold": 0.008,
|
| 49 |
+
"lr_adaptive_min": 1e-06,
|
| 50 |
+
"lr_adaptive_max": 0.01,
|
| 51 |
"obs_subtract_mean": 0.0,
|
| 52 |
"obs_scale": 255.0,
|
| 53 |
"normalize_input": true,
|
|
|
|
| 130 |
"wide_aspect_ratio": false,
|
| 131 |
"eval_env_frameskip": 1,
|
| 132 |
"fps": 35,
|
| 133 |
+
"command_line": "--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=8000000",
|
| 134 |
"cli_args": {
|
| 135 |
"env": "doom_health_gathering_supreme",
|
| 136 |
"num_workers": 8,
|
| 137 |
"num_envs_per_worker": 4,
|
| 138 |
+
"train_for_env_steps": 8000000
|
| 139 |
},
|
| 140 |
"git_hash": "unknown",
|
| 141 |
+
"git_repo_name": "not a git repository"
|
|
|
|
| 142 |
}
|
replay.mp4
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c73aa869da7b0ec6631a62eba626b02b002c9998554373ae8d5adef0f2fe691
|
| 3 |
+
size 24921021
|
sf_log.txt
ADDED
|
@@ -0,0 +1,828 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[2024-11-12 19:52:21,455][4080366] Saving configuration to /media/kemove/17a64fef-179c-4620-a965-511df0584b38/home/yunpeng/transformers/deep-rl-class-main/notebooks/unit8/train_dir/default_experiment/config.json...
|
| 2 |
+
[2024-11-12 19:52:21,455][4080366] Rollout worker 0 uses device cpu
|
| 3 |
+
[2024-11-12 19:52:21,455][4080366] Rollout worker 1 uses device cpu
|
| 4 |
+
[2024-11-12 19:52:21,456][4080366] Rollout worker 2 uses device cpu
|
| 5 |
+
[2024-11-12 19:52:21,456][4080366] Rollout worker 3 uses device cpu
|
| 6 |
+
[2024-11-12 19:52:21,456][4080366] Rollout worker 4 uses device cpu
|
| 7 |
+
[2024-11-12 19:52:21,456][4080366] Rollout worker 5 uses device cpu
|
| 8 |
+
[2024-11-12 19:52:21,457][4080366] Rollout worker 6 uses device cpu
|
| 9 |
+
[2024-11-12 19:52:21,457][4080366] Rollout worker 7 uses device cpu
|
| 10 |
+
[2024-11-12 19:52:21,557][4080366] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
| 11 |
+
[2024-11-12 19:52:21,558][4080366] InferenceWorker_p0-w0: min num requests: 2
|
| 12 |
+
[2024-11-12 19:52:21,577][4080366] Starting all processes...
|
| 13 |
+
[2024-11-12 19:52:21,578][4080366] Starting process learner_proc0
|
| 14 |
+
[2024-11-12 19:52:22,191][4080366] Starting all processes...
|
| 15 |
+
[2024-11-12 19:52:22,216][4080366] Starting process inference_proc0-0
|
| 16 |
+
[2024-11-12 19:52:22,217][4080366] Starting process rollout_proc0
|
| 17 |
+
[2024-11-12 19:52:22,217][4080366] Starting process rollout_proc1
|
| 18 |
+
[2024-11-12 19:52:22,217][4080366] Starting process rollout_proc2
|
| 19 |
+
[2024-11-12 19:52:22,217][4080366] Starting process rollout_proc3
|
| 20 |
+
[2024-11-12 19:52:22,217][4080366] Starting process rollout_proc4
|
| 21 |
+
[2024-11-12 19:52:22,217][4080366] Starting process rollout_proc5
|
| 22 |
+
[2024-11-12 19:52:22,217][4080366] Starting process rollout_proc6
|
| 23 |
+
[2024-11-12 19:52:22,218][4080366] Starting process rollout_proc7
|
| 24 |
+
[2024-11-12 19:52:23,438][4080811] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
| 25 |
+
[2024-11-12 19:52:23,438][4080811] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
|
| 26 |
+
[2024-11-12 19:52:23,447][4080816] Worker 5 uses CPU cores [15, 16, 17]
|
| 27 |
+
[2024-11-12 19:52:23,467][4080812] Worker 1 uses CPU cores [3, 4, 5]
|
| 28 |
+
[2024-11-12 19:52:23,474][4080814] Worker 2 uses CPU cores [6, 7, 8]
|
| 29 |
+
[2024-11-12 19:52:23,474][4080815] Worker 3 uses CPU cores [9, 10, 11]
|
| 30 |
+
[2024-11-12 19:52:23,476][4080817] Worker 4 uses CPU cores [12, 13, 14]
|
| 31 |
+
[2024-11-12 19:52:23,477][4080798] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
| 32 |
+
[2024-11-12 19:52:23,477][4080798] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
|
| 33 |
+
[2024-11-12 19:52:23,481][4080811] Num visible devices: 1
|
| 34 |
+
[2024-11-12 19:52:23,527][4080798] Num visible devices: 1
|
| 35 |
+
[2024-11-12 19:52:23,558][4080798] Starting seed is not provided
|
| 36 |
+
[2024-11-12 19:52:23,558][4080798] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
| 37 |
+
[2024-11-12 19:52:23,558][4080798] Initializing actor-critic model on device cuda:0
|
| 38 |
+
[2024-11-12 19:52:23,559][4080798] RunningMeanStd input shape: (3, 72, 128)
|
| 39 |
+
[2024-11-12 19:52:23,559][4080798] RunningMeanStd input shape: (1,)
|
| 40 |
+
[2024-11-12 19:52:23,570][4080798] ConvEncoder: input_channels=3
|
| 41 |
+
[2024-11-12 19:52:23,588][4080818] Worker 6 uses CPU cores [18, 19, 20]
|
| 42 |
+
[2024-11-12 19:52:23,633][4080813] Worker 0 uses CPU cores [0, 1, 2]
|
| 43 |
+
[2024-11-12 19:52:23,722][4080819] Worker 7 uses CPU cores [21, 22, 23]
|
| 44 |
+
[2024-11-12 19:52:24,116][4080798] Conv encoder output size: 512
|
| 45 |
+
[2024-11-12 19:52:24,116][4080798] Policy head output size: 512
|
| 46 |
+
[2024-11-12 19:52:24,123][4080798] Created Actor Critic model with architecture:
|
| 47 |
+
[2024-11-12 19:52:24,123][4080798] ActorCriticSharedWeights(
|
| 48 |
+
(obs_normalizer): ObservationNormalizer(
|
| 49 |
+
(running_mean_std): RunningMeanStdDictInPlace(
|
| 50 |
+
(running_mean_std): ModuleDict(
|
| 51 |
+
(obs): RunningMeanStdInPlace()
|
| 52 |
+
)
|
| 53 |
+
)
|
| 54 |
+
)
|
| 55 |
+
(returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
|
| 56 |
+
(encoder): VizdoomEncoder(
|
| 57 |
+
(basic_encoder): ConvEncoder(
|
| 58 |
+
(enc): RecursiveScriptModule(
|
| 59 |
+
original_name=ConvEncoderImpl
|
| 60 |
+
(conv_head): RecursiveScriptModule(
|
| 61 |
+
original_name=Sequential
|
| 62 |
+
(0): RecursiveScriptModule(original_name=Conv2d)
|
| 63 |
+
(1): RecursiveScriptModule(original_name=ELU)
|
| 64 |
+
(2): RecursiveScriptModule(original_name=Conv2d)
|
| 65 |
+
(3): RecursiveScriptModule(original_name=ELU)
|
| 66 |
+
(4): RecursiveScriptModule(original_name=Conv2d)
|
| 67 |
+
(5): RecursiveScriptModule(original_name=ELU)
|
| 68 |
+
)
|
| 69 |
+
(mlp_layers): RecursiveScriptModule(
|
| 70 |
+
original_name=Sequential
|
| 71 |
+
(0): RecursiveScriptModule(original_name=Linear)
|
| 72 |
+
(1): RecursiveScriptModule(original_name=ELU)
|
| 73 |
+
)
|
| 74 |
+
)
|
| 75 |
+
)
|
| 76 |
+
)
|
| 77 |
+
(core): ModelCoreRNN(
|
| 78 |
+
(core): GRU(512, 512)
|
| 79 |
+
)
|
| 80 |
+
(decoder): MlpDecoder(
|
| 81 |
+
(mlp): Identity()
|
| 82 |
+
)
|
| 83 |
+
(critic_linear): Linear(in_features=512, out_features=1, bias=True)
|
| 84 |
+
(action_parameterization): ActionParameterizationDefault(
|
| 85 |
+
(distribution_linear): Linear(in_features=512, out_features=5, bias=True)
|
| 86 |
+
)
|
| 87 |
+
)
|
| 88 |
+
[2024-11-12 19:52:24,454][4080798] Using optimizer <class 'torch.optim.adam.Adam'>
|
| 89 |
+
[2024-11-12 19:52:24,811][4080798] No checkpoints found
|
| 90 |
+
[2024-11-12 19:52:24,811][4080798] Did not load from checkpoint, starting from scratch!
|
| 91 |
+
[2024-11-12 19:52:24,811][4080798] Initialized policy 0 weights for model version 0
|
| 92 |
+
[2024-11-12 19:52:24,812][4080798] LearnerWorker_p0 finished initialization!
|
| 93 |
+
[2024-11-12 19:52:24,812][4080798] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
| 94 |
+
[2024-11-12 19:52:24,883][4080811] RunningMeanStd input shape: (3, 72, 128)
|
| 95 |
+
[2024-11-12 19:52:24,884][4080811] RunningMeanStd input shape: (1,)
|
| 96 |
+
[2024-11-12 19:52:24,890][4080811] ConvEncoder: input_channels=3
|
| 97 |
+
[2024-11-12 19:52:24,936][4080811] Conv encoder output size: 512
|
| 98 |
+
[2024-11-12 19:52:24,936][4080811] Policy head output size: 512
|
| 99 |
+
[2024-11-12 19:52:24,964][4080366] Inference worker 0-0 is ready!
|
| 100 |
+
[2024-11-12 19:52:24,965][4080366] All inference workers are ready! Signal rollout workers to start!
|
| 101 |
+
[2024-11-12 19:52:25,000][4080814] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 102 |
+
[2024-11-12 19:52:25,000][4080813] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 103 |
+
[2024-11-12 19:52:25,000][4080817] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 104 |
+
[2024-11-12 19:52:25,000][4080815] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 105 |
+
[2024-11-12 19:52:25,000][4080812] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 106 |
+
[2024-11-12 19:52:25,001][4080816] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 107 |
+
[2024-11-12 19:52:25,008][4080819] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 108 |
+
[2024-11-12 19:52:25,011][4080818] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 109 |
+
[2024-11-12 19:52:25,322][4080366] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
|
| 110 |
+
[2024-11-12 19:52:25,444][4080817] Decorrelating experience for 0 frames...
|
| 111 |
+
[2024-11-12 19:52:25,446][4080815] Decorrelating experience for 0 frames...
|
| 112 |
+
[2024-11-12 19:52:25,448][4080816] Decorrelating experience for 0 frames...
|
| 113 |
+
[2024-11-12 19:52:25,449][4080819] Decorrelating experience for 0 frames...
|
| 114 |
+
[2024-11-12 19:52:25,581][4080815] Decorrelating experience for 32 frames...
|
| 115 |
+
[2024-11-12 19:52:25,586][4080812] Decorrelating experience for 0 frames...
|
| 116 |
+
[2024-11-12 19:52:25,662][4080816] Decorrelating experience for 32 frames...
|
| 117 |
+
[2024-11-12 19:52:25,723][4080812] Decorrelating experience for 32 frames...
|
| 118 |
+
[2024-11-12 19:52:25,732][4080817] Decorrelating experience for 32 frames...
|
| 119 |
+
[2024-11-12 19:52:25,897][4080817] Decorrelating experience for 64 frames...
|
| 120 |
+
[2024-11-12 19:52:25,919][4080819] Decorrelating experience for 32 frames...
|
| 121 |
+
[2024-11-12 19:52:25,924][4080816] Decorrelating experience for 64 frames...
|
| 122 |
+
[2024-11-12 19:52:25,978][4080818] Decorrelating experience for 0 frames...
|
| 123 |
+
[2024-11-12 19:52:26,046][4080817] Decorrelating experience for 96 frames...
|
| 124 |
+
[2024-11-12 19:52:26,094][4080812] Decorrelating experience for 64 frames...
|
| 125 |
+
[2024-11-12 19:52:26,150][4080816] Decorrelating experience for 96 frames...
|
| 126 |
+
[2024-11-12 19:52:26,151][4080815] Decorrelating experience for 64 frames...
|
| 127 |
+
[2024-11-12 19:52:26,193][4080818] Decorrelating experience for 32 frames...
|
| 128 |
+
[2024-11-12 19:52:26,288][4080819] Decorrelating experience for 64 frames...
|
| 129 |
+
[2024-11-12 19:52:26,290][4080812] Decorrelating experience for 96 frames...
|
| 130 |
+
[2024-11-12 19:52:26,291][4080815] Decorrelating experience for 96 frames...
|
| 131 |
+
[2024-11-12 19:52:26,455][4080818] Decorrelating experience for 64 frames...
|
| 132 |
+
[2024-11-12 19:52:26,519][4080819] Decorrelating experience for 96 frames...
|
| 133 |
+
[2024-11-12 19:52:26,681][4080818] Decorrelating experience for 96 frames...
|
| 134 |
+
[2024-11-12 19:52:29,589][4080798] Signal inference workers to stop experience collection...
|
| 135 |
+
[2024-11-12 19:52:29,592][4080811] InferenceWorker_p0-w0: stopping experience collection
|
| 136 |
+
[2024-11-12 19:52:30,322][4080366] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 5.6. Samples: 28. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
|
| 137 |
+
[2024-11-12 19:52:30,325][4080366] Avg episode reward: [(0, '2.638')]
|
| 138 |
+
[2024-11-12 19:52:34,741][4080798] Signal inference workers to resume experience collection...
|
| 139 |
+
[2024-11-12 19:52:34,741][4080811] InferenceWorker_p0-w0: resuming experience collection
|
| 140 |
+
[2024-11-12 19:52:35,321][4080366] Fps is (10 sec: 1638.5, 60 sec: 1638.5, 300 sec: 1638.5). Total num frames: 16384. Throughput: 0: 238.2. Samples: 2382. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
|
| 141 |
+
[2024-11-12 19:52:35,322][4080366] Avg episode reward: [(0, '3.726')]
|
| 142 |
+
[2024-11-12 19:52:35,990][4080811] Updated weights for policy 0, policy_version 10 (0.0186)
|
| 143 |
+
[2024-11-12 19:52:37,286][4080811] Updated weights for policy 0, policy_version 20 (0.0007)
|
| 144 |
+
[2024-11-12 19:52:38,492][4080811] Updated weights for policy 0, policy_version 30 (0.0005)
|
| 145 |
+
[2024-11-12 19:52:39,775][4080811] Updated weights for policy 0, policy_version 40 (0.0006)
|
| 146 |
+
[2024-11-12 19:52:40,321][4080366] Fps is (10 sec: 18023.6, 60 sec: 12015.4, 300 sec: 12015.4). Total num frames: 180224. Throughput: 0: 2887.3. Samples: 43308. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 147 |
+
[2024-11-12 19:52:40,322][4080366] Avg episode reward: [(0, '4.426')]
|
| 148 |
+
[2024-11-12 19:52:40,343][4080798] Saving new best policy, reward=4.426!
|
| 149 |
+
[2024-11-12 19:52:40,999][4080811] Updated weights for policy 0, policy_version 50 (0.0006)
|
| 150 |
+
[2024-11-12 19:52:41,553][4080366] Heartbeat connected on LearnerWorker_p0
|
| 151 |
+
[2024-11-12 19:52:41,557][4080366] Heartbeat connected on Batcher_0
|
| 152 |
+
[2024-11-12 19:52:41,563][4080366] Heartbeat connected on InferenceWorker_p0-w0
|
| 153 |
+
[2024-11-12 19:52:41,566][4080366] Heartbeat connected on RolloutWorker_w1
|
| 154 |
+
[2024-11-12 19:52:41,571][4080366] Heartbeat connected on RolloutWorker_w3
|
| 155 |
+
[2024-11-12 19:52:41,571][4080366] Heartbeat connected on RolloutWorker_w4
|
| 156 |
+
[2024-11-12 19:52:41,573][4080366] Heartbeat connected on RolloutWorker_w5
|
| 157 |
+
[2024-11-12 19:52:41,575][4080366] Heartbeat connected on RolloutWorker_w6
|
| 158 |
+
[2024-11-12 19:52:41,580][4080366] Heartbeat connected on RolloutWorker_w7
|
| 159 |
+
[2024-11-12 19:52:42,204][4080811] Updated weights for policy 0, policy_version 60 (0.0006)
|
| 160 |
+
[2024-11-12 19:52:43,423][4080811] Updated weights for policy 0, policy_version 70 (0.0006)
|
| 161 |
+
[2024-11-12 19:52:44,641][4080811] Updated weights for policy 0, policy_version 80 (0.0005)
|
| 162 |
+
[2024-11-12 19:52:45,321][4080366] Fps is (10 sec: 33177.5, 60 sec: 17408.4, 300 sec: 17408.4). Total num frames: 348160. Throughput: 0: 3410.1. Samples: 68200. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 163 |
+
[2024-11-12 19:52:45,322][4080366] Avg episode reward: [(0, '4.315')]
|
| 164 |
+
[2024-11-12 19:52:45,826][4080811] Updated weights for policy 0, policy_version 90 (0.0005)
|
| 165 |
+
[2024-11-12 19:52:47,006][4080811] Updated weights for policy 0, policy_version 100 (0.0005)
|
| 166 |
+
[2024-11-12 19:52:48,164][4080811] Updated weights for policy 0, policy_version 110 (0.0006)
|
| 167 |
+
[2024-11-12 19:52:49,316][4080811] Updated weights for policy 0, policy_version 120 (0.0005)
|
| 168 |
+
[2024-11-12 19:52:50,321][4080366] Fps is (10 sec: 34405.3, 60 sec: 20971.7, 300 sec: 20971.7). Total num frames: 524288. Throughput: 0: 4811.7. Samples: 120292. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
| 169 |
+
[2024-11-12 19:52:50,322][4080366] Avg episode reward: [(0, '4.520')]
|
| 170 |
+
[2024-11-12 19:52:50,326][4080798] Saving new best policy, reward=4.520!
|
| 171 |
+
[2024-11-12 19:52:50,476][4080811] Updated weights for policy 0, policy_version 130 (0.0005)
|
| 172 |
+
[2024-11-12 19:52:51,623][4080811] Updated weights for policy 0, policy_version 140 (0.0005)
|
| 173 |
+
[2024-11-12 19:52:52,757][4080811] Updated weights for policy 0, policy_version 150 (0.0005)
|
| 174 |
+
[2024-11-12 19:52:53,932][4080811] Updated weights for policy 0, policy_version 160 (0.0006)
|
| 175 |
+
[2024-11-12 19:52:55,125][4080811] Updated weights for policy 0, policy_version 170 (0.0006)
|
| 176 |
+
[2024-11-12 19:52:55,321][4080366] Fps is (10 sec: 35225.6, 60 sec: 23347.6, 300 sec: 23347.6). Total num frames: 700416. Throughput: 0: 5779.0. Samples: 173368. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
|
| 177 |
+
[2024-11-12 19:52:55,322][4080366] Avg episode reward: [(0, '4.636')]
|
| 178 |
+
[2024-11-12 19:52:55,323][4080798] Saving new best policy, reward=4.636!
|
| 179 |
+
[2024-11-12 19:52:56,359][4080811] Updated weights for policy 0, policy_version 180 (0.0006)
|
| 180 |
+
[2024-11-12 19:52:57,539][4080811] Updated weights for policy 0, policy_version 190 (0.0005)
|
| 181 |
+
[2024-11-12 19:52:58,856][4080811] Updated weights for policy 0, policy_version 200 (0.0005)
|
| 182 |
+
[2024-11-12 19:53:00,042][4080811] Updated weights for policy 0, policy_version 210 (0.0005)
|
| 183 |
+
[2024-11-12 19:53:00,321][4080366] Fps is (10 sec: 34407.1, 60 sec: 24810.4, 300 sec: 24810.4). Total num frames: 868352. Throughput: 0: 5668.5. Samples: 198394. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
|
| 184 |
+
[2024-11-12 19:53:00,322][4080366] Avg episode reward: [(0, '4.573')]
|
| 185 |
+
[2024-11-12 19:53:01,307][4080811] Updated weights for policy 0, policy_version 220 (0.0005)
|
| 186 |
+
[2024-11-12 19:53:02,524][4080811] Updated weights for policy 0, policy_version 230 (0.0006)
|
| 187 |
+
[2024-11-12 19:53:03,789][4080811] Updated weights for policy 0, policy_version 240 (0.0006)
|
| 188 |
+
[2024-11-12 19:53:04,964][4080811] Updated weights for policy 0, policy_version 250 (0.0005)
|
| 189 |
+
[2024-11-12 19:53:05,321][4080366] Fps is (10 sec: 33177.9, 60 sec: 25805.2, 300 sec: 25805.2). Total num frames: 1032192. Throughput: 0: 6195.6. Samples: 247822. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 190 |
+
[2024-11-12 19:53:05,322][4080366] Avg episode reward: [(0, '4.831')]
|
| 191 |
+
[2024-11-12 19:53:05,339][4080798] Saving new best policy, reward=4.831!
|
| 192 |
+
[2024-11-12 19:53:06,199][4080811] Updated weights for policy 0, policy_version 260 (0.0005)
|
| 193 |
+
[2024-11-12 19:53:07,374][4080811] Updated weights for policy 0, policy_version 270 (0.0005)
|
| 194 |
+
[2024-11-12 19:53:08,535][4080811] Updated weights for policy 0, policy_version 280 (0.0006)
|
| 195 |
+
[2024-11-12 19:53:09,725][4080811] Updated weights for policy 0, policy_version 290 (0.0005)
|
| 196 |
+
[2024-11-12 19:53:10,321][4080366] Fps is (10 sec: 33587.4, 60 sec: 26760.8, 300 sec: 26760.8). Total num frames: 1204224. Throughput: 0: 6656.6. Samples: 299542. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
| 197 |
+
[2024-11-12 19:53:10,322][4080366] Avg episode reward: [(0, '5.176')]
|
| 198 |
+
[2024-11-12 19:53:10,338][4080798] Saving new best policy, reward=5.176!
|
| 199 |
+
[2024-11-12 19:53:10,967][4080811] Updated weights for policy 0, policy_version 300 (0.0006)
|
| 200 |
+
[2024-11-12 19:53:12,166][4080811] Updated weights for policy 0, policy_version 310 (0.0006)
|
| 201 |
+
[2024-11-12 19:53:13,332][4080811] Updated weights for policy 0, policy_version 320 (0.0006)
|
| 202 |
+
[2024-11-12 19:53:14,540][4080811] Updated weights for policy 0, policy_version 330 (0.0005)
|
| 203 |
+
[2024-11-12 19:53:15,321][4080366] Fps is (10 sec: 34406.4, 60 sec: 27525.4, 300 sec: 27525.4). Total num frames: 1376256. Throughput: 0: 7217.0. Samples: 324790. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
| 204 |
+
[2024-11-12 19:53:15,322][4080366] Avg episode reward: [(0, '5.563')]
|
| 205 |
+
[2024-11-12 19:53:15,323][4080798] Saving new best policy, reward=5.563!
|
| 206 |
+
[2024-11-12 19:53:15,772][4080811] Updated weights for policy 0, policy_version 340 (0.0005)
|
| 207 |
+
[2024-11-12 19:53:16,953][4080811] Updated weights for policy 0, policy_version 350 (0.0006)
|
| 208 |
+
[2024-11-12 19:53:18,355][4080811] Updated weights for policy 0, policy_version 360 (0.0007)
|
| 209 |
+
[2024-11-12 19:53:19,675][4080811] Updated weights for policy 0, policy_version 370 (0.0006)
|
| 210 |
+
[2024-11-12 19:53:20,321][4080366] Fps is (10 sec: 32768.3, 60 sec: 27853.1, 300 sec: 27853.1). Total num frames: 1531904. Throughput: 0: 8255.6. Samples: 373882. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 211 |
+
[2024-11-12 19:53:20,322][4080366] Avg episode reward: [(0, '6.977')]
|
| 212 |
+
[2024-11-12 19:53:20,325][4080798] Saving new best policy, reward=6.977!
|
| 213 |
+
[2024-11-12 19:53:20,994][4080811] Updated weights for policy 0, policy_version 380 (0.0006)
|
| 214 |
+
[2024-11-12 19:53:22,301][4080811] Updated weights for policy 0, policy_version 390 (0.0006)
|
| 215 |
+
[2024-11-12 19:53:23,657][4080811] Updated weights for policy 0, policy_version 400 (0.0007)
|
| 216 |
+
[2024-11-12 19:53:24,971][4080811] Updated weights for policy 0, policy_version 410 (0.0007)
|
| 217 |
+
[2024-11-12 19:53:25,321][4080366] Fps is (10 sec: 31129.4, 60 sec: 28126.1, 300 sec: 28126.1). Total num frames: 1687552. Throughput: 0: 8380.0. Samples: 420410. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
|
| 218 |
+
[2024-11-12 19:53:25,322][4080366] Avg episode reward: [(0, '8.040')]
|
| 219 |
+
[2024-11-12 19:53:25,323][4080798] Saving new best policy, reward=8.040!
|
| 220 |
+
[2024-11-12 19:53:26,341][4080811] Updated weights for policy 0, policy_version 420 (0.0006)
|
| 221 |
+
[2024-11-12 19:53:27,629][4080811] Updated weights for policy 0, policy_version 430 (0.0007)
|
| 222 |
+
[2024-11-12 19:53:28,946][4080811] Updated weights for policy 0, policy_version 440 (0.0006)
|
| 223 |
+
[2024-11-12 19:53:30,242][4080811] Updated weights for policy 0, policy_version 450 (0.0006)
|
| 224 |
+
[2024-11-12 19:53:30,321][4080366] Fps is (10 sec: 31129.3, 60 sec: 30720.3, 300 sec: 28357.1). Total num frames: 1843200. Throughput: 0: 8339.3. Samples: 443470. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 225 |
+
[2024-11-12 19:53:30,322][4080366] Avg episode reward: [(0, '9.563')]
|
| 226 |
+
[2024-11-12 19:53:30,324][4080798] Saving new best policy, reward=9.563!
|
| 227 |
+
[2024-11-12 19:53:31,542][4080811] Updated weights for policy 0, policy_version 460 (0.0008)
|
| 228 |
+
[2024-11-12 19:53:32,828][4080811] Updated weights for policy 0, policy_version 470 (0.0007)
|
| 229 |
+
[2024-11-12 19:53:34,122][4080811] Updated weights for policy 0, policy_version 480 (0.0007)
|
| 230 |
+
[2024-11-12 19:53:35,321][4080366] Fps is (10 sec: 31538.8, 60 sec: 33109.2, 300 sec: 28613.6). Total num frames: 2002944. Throughput: 0: 8235.5. Samples: 490890. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 231 |
+
[2024-11-12 19:53:35,322][4080366] Avg episode reward: [(0, '13.531')]
|
| 232 |
+
[2024-11-12 19:53:35,323][4080798] Saving new best policy, reward=13.531!
|
| 233 |
+
[2024-11-12 19:53:35,451][4080811] Updated weights for policy 0, policy_version 490 (0.0008)
|
| 234 |
+
[2024-11-12 19:53:36,761][4080811] Updated weights for policy 0, policy_version 500 (0.0008)
|
| 235 |
+
[2024-11-12 19:53:38,096][4080811] Updated weights for policy 0, policy_version 510 (0.0007)
|
| 236 |
+
[2024-11-12 19:53:39,399][4080811] Updated weights for policy 0, policy_version 520 (0.0007)
|
| 237 |
+
[2024-11-12 19:53:40,321][4080366] Fps is (10 sec: 31128.9, 60 sec: 32904.4, 300 sec: 28726.7). Total num frames: 2154496. Throughput: 0: 8089.3. Samples: 537386. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 238 |
+
[2024-11-12 19:53:40,322][4080366] Avg episode reward: [(0, '11.571')]
|
| 239 |
+
[2024-11-12 19:53:40,732][4080811] Updated weights for policy 0, policy_version 530 (0.0008)
|
| 240 |
+
[2024-11-12 19:53:42,064][4080811] Updated weights for policy 0, policy_version 540 (0.0007)
|
| 241 |
+
[2024-11-12 19:53:43,380][4080811] Updated weights for policy 0, policy_version 550 (0.0007)
|
| 242 |
+
[2024-11-12 19:53:44,668][4080811] Updated weights for policy 0, policy_version 560 (0.0006)
|
| 243 |
+
[2024-11-12 19:53:45,321][4080366] Fps is (10 sec: 31129.4, 60 sec: 32767.9, 300 sec: 28928.1). Total num frames: 2314240. Throughput: 0: 8048.8. Samples: 560592. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
| 244 |
+
[2024-11-12 19:53:45,323][4080366] Avg episode reward: [(0, '14.270')]
|
| 245 |
+
[2024-11-12 19:53:45,324][4080798] Saving new best policy, reward=14.270!
|
| 246 |
+
[2024-11-12 19:53:45,962][4080811] Updated weights for policy 0, policy_version 570 (0.0007)
|
| 247 |
+
[2024-11-12 19:53:47,236][4080811] Updated weights for policy 0, policy_version 580 (0.0007)
|
| 248 |
+
[2024-11-12 19:53:48,505][4080811] Updated weights for policy 0, policy_version 590 (0.0006)
|
| 249 |
+
[2024-11-12 19:53:49,793][4080811] Updated weights for policy 0, policy_version 600 (0.0007)
|
| 250 |
+
[2024-11-12 19:53:50,321][4080366] Fps is (10 sec: 31949.1, 60 sec: 32495.0, 300 sec: 29105.8). Total num frames: 2473984. Throughput: 0: 8007.6. Samples: 608166. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 251 |
+
[2024-11-12 19:53:50,322][4080366] Avg episode reward: [(0, '18.421')]
|
| 252 |
+
[2024-11-12 19:53:50,324][4080798] Saving new best policy, reward=18.421!
|
| 253 |
+
[2024-11-12 19:53:51,090][4080811] Updated weights for policy 0, policy_version 610 (0.0007)
|
| 254 |
+
[2024-11-12 19:53:52,345][4080811] Updated weights for policy 0, policy_version 620 (0.0006)
|
| 255 |
+
[2024-11-12 19:53:53,607][4080811] Updated weights for policy 0, policy_version 630 (0.0007)
|
| 256 |
+
[2024-11-12 19:53:54,903][4080811] Updated weights for policy 0, policy_version 640 (0.0007)
|
| 257 |
+
[2024-11-12 19:53:55,321][4080366] Fps is (10 sec: 31948.9, 60 sec: 32221.8, 300 sec: 29263.7). Total num frames: 2633728. Throughput: 0: 7931.1. Samples: 656444. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
|
| 258 |
+
[2024-11-12 19:53:55,322][4080366] Avg episode reward: [(0, '17.658')]
|
| 259 |
+
[2024-11-12 19:53:56,195][4080811] Updated weights for policy 0, policy_version 650 (0.0006)
|
| 260 |
+
[2024-11-12 19:53:57,483][4080811] Updated weights for policy 0, policy_version 660 (0.0007)
|
| 261 |
+
[2024-11-12 19:53:58,751][4080811] Updated weights for policy 0, policy_version 670 (0.0007)
|
| 262 |
+
[2024-11-12 19:54:00,013][4080811] Updated weights for policy 0, policy_version 680 (0.0006)
|
| 263 |
+
[2024-11-12 19:54:00,321][4080366] Fps is (10 sec: 31948.8, 60 sec: 32085.3, 300 sec: 29405.1). Total num frames: 2793472. Throughput: 0: 7900.4. Samples: 680308. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 264 |
+
[2024-11-12 19:54:00,322][4080366] Avg episode reward: [(0, '19.218')]
|
| 265 |
+
[2024-11-12 19:54:00,324][4080798] Saving new best policy, reward=19.218!
|
| 266 |
+
[2024-11-12 19:54:01,308][4080811] Updated weights for policy 0, policy_version 690 (0.0007)
|
| 267 |
+
[2024-11-12 19:54:02,563][4080811] Updated weights for policy 0, policy_version 700 (0.0007)
|
| 268 |
+
[2024-11-12 19:54:03,873][4080811] Updated weights for policy 0, policy_version 710 (0.0007)
|
| 269 |
+
[2024-11-12 19:54:05,163][4080811] Updated weights for policy 0, policy_version 720 (0.0007)
|
| 270 |
+
[2024-11-12 19:54:05,321][4080366] Fps is (10 sec: 31949.5, 60 sec: 32017.0, 300 sec: 29532.3). Total num frames: 2953216. Throughput: 0: 7872.6. Samples: 728150. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
| 271 |
+
[2024-11-12 19:54:05,322][4080366] Avg episode reward: [(0, '20.431')]
|
| 272 |
+
[2024-11-12 19:54:05,322][4080798] Saving new best policy, reward=20.431!
|
| 273 |
+
[2024-11-12 19:54:06,499][4080811] Updated weights for policy 0, policy_version 730 (0.0007)
|
| 274 |
+
[2024-11-12 19:54:07,813][4080811] Updated weights for policy 0, policy_version 740 (0.0007)
|
| 275 |
+
[2024-11-12 19:54:09,097][4080811] Updated weights for policy 0, policy_version 750 (0.0007)
|
| 276 |
+
[2024-11-12 19:54:10,321][4080366] Fps is (10 sec: 31539.3, 60 sec: 31744.0, 300 sec: 29608.4). Total num frames: 3108864. Throughput: 0: 7883.9. Samples: 775188. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
| 277 |
+
[2024-11-12 19:54:10,322][4080366] Avg episode reward: [(0, '21.010')]
|
| 278 |
+
[2024-11-12 19:54:10,325][4080798] Saving new best policy, reward=21.010!
|
| 279 |
+
[2024-11-12 19:54:10,442][4080811] Updated weights for policy 0, policy_version 760 (0.0006)
|
| 280 |
+
[2024-11-12 19:54:11,730][4080811] Updated weights for policy 0, policy_version 770 (0.0007)
|
| 281 |
+
[2024-11-12 19:54:13,003][4080811] Updated weights for policy 0, policy_version 780 (0.0007)
|
| 282 |
+
[2024-11-12 19:54:14,292][4080811] Updated weights for policy 0, policy_version 790 (0.0006)
|
| 283 |
+
[2024-11-12 19:54:15,321][4080366] Fps is (10 sec: 31538.6, 60 sec: 31539.1, 300 sec: 29714.7). Total num frames: 3268608. Throughput: 0: 7896.5. Samples: 798812. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 284 |
+
[2024-11-12 19:54:15,322][4080366] Avg episode reward: [(0, '19.712')]
|
| 285 |
+
[2024-11-12 19:54:15,591][4080811] Updated weights for policy 0, policy_version 800 (0.0007)
|
| 286 |
+
[2024-11-12 19:54:16,927][4080811] Updated weights for policy 0, policy_version 810 (0.0008)
|
| 287 |
+
[2024-11-12 19:54:18,182][4080811] Updated weights for policy 0, policy_version 820 (0.0007)
|
| 288 |
+
[2024-11-12 19:54:19,484][4080811] Updated weights for policy 0, policy_version 830 (0.0007)
|
| 289 |
+
[2024-11-12 19:54:20,321][4080366] Fps is (10 sec: 31539.1, 60 sec: 31539.1, 300 sec: 29776.2). Total num frames: 3424256. Throughput: 0: 7894.8. Samples: 846156. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
| 290 |
+
[2024-11-12 19:54:20,322][4080366] Avg episode reward: [(0, '20.980')]
|
| 291 |
+
[2024-11-12 19:54:20,325][4080798] Saving /media/kemove/17a64fef-179c-4620-a965-511df0584b38/home/yunpeng/transformers/deep-rl-class-main/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000836_3424256.pth...
|
| 292 |
+
[2024-11-12 19:54:20,821][4080811] Updated weights for policy 0, policy_version 840 (0.0007)
|
| 293 |
+
[2024-11-12 19:54:22,091][4080811] Updated weights for policy 0, policy_version 850 (0.0006)
|
| 294 |
+
[2024-11-12 19:54:23,347][4080811] Updated weights for policy 0, policy_version 860 (0.0007)
|
| 295 |
+
[2024-11-12 19:54:24,660][4080811] Updated weights for policy 0, policy_version 870 (0.0007)
|
| 296 |
+
[2024-11-12 19:54:25,321][4080366] Fps is (10 sec: 31539.4, 60 sec: 31607.4, 300 sec: 29866.8). Total num frames: 3584000. Throughput: 0: 7924.6. Samples: 893990. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
|
| 297 |
+
[2024-11-12 19:54:25,322][4080366] Avg episode reward: [(0, '24.097')]
|
| 298 |
+
[2024-11-12 19:54:25,323][4080798] Saving new best policy, reward=24.097!
|
| 299 |
+
[2024-11-12 19:54:25,927][4080811] Updated weights for policy 0, policy_version 880 (0.0007)
|
| 300 |
+
[2024-11-12 19:54:27,263][4080811] Updated weights for policy 0, policy_version 890 (0.0007)
|
| 301 |
+
[2024-11-12 19:54:28,511][4080811] Updated weights for policy 0, policy_version 900 (0.0006)
|
| 302 |
+
[2024-11-12 19:54:29,754][4080811] Updated weights for policy 0, policy_version 910 (0.0007)
|
| 303 |
+
[2024-11-12 19:54:30,321][4080366] Fps is (10 sec: 31949.2, 60 sec: 31675.7, 300 sec: 29950.1). Total num frames: 3743744. Throughput: 0: 7933.9. Samples: 917618. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
| 304 |
+
[2024-11-12 19:54:30,322][4080366] Avg episode reward: [(0, '19.775')]
|
| 305 |
+
[2024-11-12 19:54:31,050][4080811] Updated weights for policy 0, policy_version 920 (0.0006)
|
| 306 |
+
[2024-11-12 19:54:32,328][4080811] Updated weights for policy 0, policy_version 930 (0.0006)
|
| 307 |
+
[2024-11-12 19:54:33,644][4080811] Updated weights for policy 0, policy_version 940 (0.0007)
|
| 308 |
+
[2024-11-12 19:54:34,921][4080811] Updated weights for policy 0, policy_version 950 (0.0007)
|
| 309 |
+
[2024-11-12 19:54:35,321][4080366] Fps is (10 sec: 31949.1, 60 sec: 31675.8, 300 sec: 30026.9). Total num frames: 3903488. Throughput: 0: 7943.9. Samples: 965640. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
|
| 310 |
+
[2024-11-12 19:54:35,322][4080366] Avg episode reward: [(0, '24.386')]
|
| 311 |
+
[2024-11-12 19:54:35,323][4080798] Saving new best policy, reward=24.386!
|
| 312 |
+
[2024-11-12 19:54:36,212][4080811] Updated weights for policy 0, policy_version 960 (0.0007)
|
| 313 |
+
[2024-11-12 19:54:37,485][4080811] Updated weights for policy 0, policy_version 970 (0.0006)
|
| 314 |
+
[2024-11-12 19:54:38,791][4080811] Updated weights for policy 0, policy_version 980 (0.0006)
|
| 315 |
+
[2024-11-12 19:54:40,162][4080811] Updated weights for policy 0, policy_version 990 (0.0008)
|
| 316 |
+
[2024-11-12 19:54:40,321][4080366] Fps is (10 sec: 31129.4, 60 sec: 31675.8, 300 sec: 30037.4). Total num frames: 4055040. Throughput: 0: 7919.0. Samples: 1012800. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 317 |
+
[2024-11-12 19:54:40,323][4080366] Avg episode reward: [(0, '20.459')]
|
| 318 |
+
[2024-11-12 19:54:41,559][4080811] Updated weights for policy 0, policy_version 1000 (0.0007)
|
| 319 |
+
[2024-11-12 19:54:42,863][4080811] Updated weights for policy 0, policy_version 1010 (0.0006)
|
| 320 |
+
[2024-11-12 19:54:44,129][4080811] Updated weights for policy 0, policy_version 1020 (0.0006)
|
| 321 |
+
[2024-11-12 19:54:45,321][4080366] Fps is (10 sec: 31129.7, 60 sec: 31675.9, 300 sec: 30105.7). Total num frames: 4214784. Throughput: 0: 7895.7. Samples: 1035614. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
|
| 322 |
+
[2024-11-12 19:54:45,322][4080366] Avg episode reward: [(0, '23.194')]
|
| 323 |
+
[2024-11-12 19:54:45,414][4080811] Updated weights for policy 0, policy_version 1030 (0.0007)
|
| 324 |
+
[2024-11-12 19:54:46,708][4080811] Updated weights for policy 0, policy_version 1040 (0.0007)
|
| 325 |
+
[2024-11-12 19:54:47,990][4080811] Updated weights for policy 0, policy_version 1050 (0.0007)
|
| 326 |
+
[2024-11-12 19:54:49,290][4080811] Updated weights for policy 0, policy_version 1060 (0.0006)
|
| 327 |
+
[2024-11-12 19:54:50,321][4080366] Fps is (10 sec: 31539.1, 60 sec: 31607.5, 300 sec: 30141.0). Total num frames: 4370432. Throughput: 0: 7895.0. Samples: 1083428. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 328 |
+
[2024-11-12 19:54:50,323][4080366] Avg episode reward: [(0, '22.905')]
|
| 329 |
+
[2024-11-12 19:54:50,575][4080811] Updated weights for policy 0, policy_version 1070 (0.0007)
|
| 330 |
+
[2024-11-12 19:54:51,844][4080811] Updated weights for policy 0, policy_version 1080 (0.0007)
|
| 331 |
+
[2024-11-12 19:54:53,146][4080811] Updated weights for policy 0, policy_version 1090 (0.0007)
|
| 332 |
+
[2024-11-12 19:54:54,425][4080811] Updated weights for policy 0, policy_version 1100 (0.0007)
|
| 333 |
+
[2024-11-12 19:54:55,321][4080366] Fps is (10 sec: 31948.2, 60 sec: 31675.7, 300 sec: 30228.6). Total num frames: 4534272. Throughput: 0: 7909.7. Samples: 1131126. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
| 334 |
+
[2024-11-12 19:54:55,322][4080366] Avg episode reward: [(0, '22.847')]
|
| 335 |
+
[2024-11-12 19:54:55,731][4080811] Updated weights for policy 0, policy_version 1110 (0.0006)
|
| 336 |
+
[2024-11-12 19:54:57,043][4080811] Updated weights for policy 0, policy_version 1120 (0.0006)
|
| 337 |
+
[2024-11-12 19:54:58,317][4080811] Updated weights for policy 0, policy_version 1130 (0.0007)
|
| 338 |
+
[2024-11-12 19:54:59,597][4080811] Updated weights for policy 0, policy_version 1140 (0.0007)
|
| 339 |
+
[2024-11-12 19:55:00,321][4080366] Fps is (10 sec: 31948.6, 60 sec: 31607.5, 300 sec: 30257.6). Total num frames: 4689920. Throughput: 0: 7910.7. Samples: 1154792. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
| 340 |
+
[2024-11-12 19:55:00,322][4080366] Avg episode reward: [(0, '22.796')]
|
| 341 |
+
[2024-11-12 19:55:00,902][4080811] Updated weights for policy 0, policy_version 1150 (0.0008)
|
| 342 |
+
[2024-11-12 19:55:02,163][4080811] Updated weights for policy 0, policy_version 1160 (0.0007)
|
| 343 |
+
[2024-11-12 19:55:03,458][4080811] Updated weights for policy 0, policy_version 1170 (0.0006)
|
| 344 |
+
[2024-11-12 19:55:04,733][4080811] Updated weights for policy 0, policy_version 1180 (0.0007)
|
| 345 |
+
[2024-11-12 19:55:05,321][4080366] Fps is (10 sec: 31539.2, 60 sec: 31607.4, 300 sec: 30310.5). Total num frames: 4849664. Throughput: 0: 7921.5. Samples: 1202622. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
| 346 |
+
[2024-11-12 19:55:05,322][4080366] Avg episode reward: [(0, '21.007')]
|
| 347 |
+
[2024-11-12 19:55:06,037][4080811] Updated weights for policy 0, policy_version 1190 (0.0007)
|
| 348 |
+
[2024-11-12 19:55:07,375][4080811] Updated weights for policy 0, policy_version 1200 (0.0007)
|
| 349 |
+
[2024-11-12 19:55:08,671][4080811] Updated weights for policy 0, policy_version 1210 (0.0007)
|
| 350 |
+
[2024-11-12 19:55:10,005][4080811] Updated weights for policy 0, policy_version 1220 (0.0007)
|
| 351 |
+
[2024-11-12 19:55:10,321][4080366] Fps is (10 sec: 31539.8, 60 sec: 31607.5, 300 sec: 30335.3). Total num frames: 5005312. Throughput: 0: 7902.2. Samples: 1249590. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
| 352 |
+
[2024-11-12 19:55:10,322][4080366] Avg episode reward: [(0, '21.686')]
|
| 353 |
+
[2024-11-12 19:55:11,313][4080811] Updated weights for policy 0, policy_version 1230 (0.0006)
|
| 354 |
+
[2024-11-12 19:55:12,624][4080811] Updated weights for policy 0, policy_version 1240 (0.0007)
|
| 355 |
+
[2024-11-12 19:55:13,925][4080811] Updated weights for policy 0, policy_version 1250 (0.0006)
|
| 356 |
+
[2024-11-12 19:55:15,236][4080811] Updated weights for policy 0, policy_version 1260 (0.0007)
|
| 357 |
+
[2024-11-12 19:55:15,321][4080366] Fps is (10 sec: 31128.7, 60 sec: 31539.1, 300 sec: 30358.6). Total num frames: 5160960. Throughput: 0: 7895.0. Samples: 1272896. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
|
| 358 |
+
[2024-11-12 19:55:15,323][4080366] Avg episode reward: [(0, '21.382')]
|
| 359 |
+
[2024-11-12 19:55:16,526][4080811] Updated weights for policy 0, policy_version 1270 (0.0007)
|
| 360 |
+
[2024-11-12 19:55:17,820][4080811] Updated weights for policy 0, policy_version 1280 (0.0007)
|
| 361 |
+
[2024-11-12 19:55:19,091][4080811] Updated weights for policy 0, policy_version 1290 (0.0006)
|
| 362 |
+
[2024-11-12 19:55:20,321][4080366] Fps is (10 sec: 31539.2, 60 sec: 31607.6, 300 sec: 30404.1). Total num frames: 5320704. Throughput: 0: 7884.1. Samples: 1320426. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
| 363 |
+
[2024-11-12 19:55:20,322][4080366] Avg episode reward: [(0, '21.192')]
|
| 364 |
+
[2024-11-12 19:55:20,389][4080811] Updated weights for policy 0, policy_version 1300 (0.0007)
|
| 365 |
+
[2024-11-12 19:55:21,712][4080811] Updated weights for policy 0, policy_version 1310 (0.0006)
|
| 366 |
+
[2024-11-12 19:55:22,986][4080811] Updated weights for policy 0, policy_version 1320 (0.0007)
|
| 367 |
+
[2024-11-12 19:55:24,274][4080811] Updated weights for policy 0, policy_version 1330 (0.0007)
|
| 368 |
+
[2024-11-12 19:55:25,321][4080366] Fps is (10 sec: 31950.0, 60 sec: 31607.5, 300 sec: 30447.0). Total num frames: 5480448. Throughput: 0: 7889.9. Samples: 1367846. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
| 369 |
+
[2024-11-12 19:55:25,322][4080366] Avg episode reward: [(0, '23.688')]
|
| 370 |
+
[2024-11-12 19:55:25,596][4080811] Updated weights for policy 0, policy_version 1340 (0.0006)
|
| 371 |
+
[2024-11-12 19:55:26,883][4080811] Updated weights for policy 0, policy_version 1350 (0.0007)
|
| 372 |
+
[2024-11-12 19:55:28,176][4080811] Updated weights for policy 0, policy_version 1360 (0.0007)
|
| 373 |
+
[2024-11-12 19:55:29,498][4080811] Updated weights for policy 0, policy_version 1370 (0.0006)
|
| 374 |
+
[2024-11-12 19:55:30,321][4080366] Fps is (10 sec: 31539.2, 60 sec: 31539.2, 300 sec: 30465.5). Total num frames: 5636096. Throughput: 0: 7906.9. Samples: 1391426. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 375 |
+
[2024-11-12 19:55:30,322][4080366] Avg episode reward: [(0, '24.751')]
|
| 376 |
+
[2024-11-12 19:55:30,324][4080798] Saving new best policy, reward=24.751!
|
| 377 |
+
[2024-11-12 19:55:30,798][4080811] Updated weights for policy 0, policy_version 1380 (0.0006)
|
| 378 |
+
[2024-11-12 19:55:32,108][4080811] Updated weights for policy 0, policy_version 1390 (0.0007)
|
| 379 |
+
[2024-11-12 19:55:33,403][4080811] Updated weights for policy 0, policy_version 1400 (0.0007)
|
| 380 |
+
[2024-11-12 19:55:34,729][4080811] Updated weights for policy 0, policy_version 1410 (0.0007)
|
| 381 |
+
[2024-11-12 19:55:35,321][4080366] Fps is (10 sec: 31130.0, 60 sec: 31471.0, 300 sec: 30483.0). Total num frames: 5791744. Throughput: 0: 7888.5. Samples: 1438410. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
|
| 382 |
+
[2024-11-12 19:55:35,322][4080366] Avg episode reward: [(0, '24.579')]
|
| 383 |
+
[2024-11-12 19:55:36,035][4080811] Updated weights for policy 0, policy_version 1420 (0.0006)
|
| 384 |
+
[2024-11-12 19:55:37,363][4080811] Updated weights for policy 0, policy_version 1430 (0.0008)
|
| 385 |
+
[2024-11-12 19:55:38,694][4080811] Updated weights for policy 0, policy_version 1440 (0.0006)
|
| 386 |
+
[2024-11-12 19:55:40,009][4080811] Updated weights for policy 0, policy_version 1450 (0.0007)
|
| 387 |
+
[2024-11-12 19:55:40,321][4080366] Fps is (10 sec: 31129.0, 60 sec: 31539.2, 300 sec: 30499.5). Total num frames: 5947392. Throughput: 0: 7865.7. Samples: 1485082. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
|
| 388 |
+
[2024-11-12 19:55:40,322][4080366] Avg episode reward: [(0, '23.786')]
|
| 389 |
+
[2024-11-12 19:55:41,320][4080811] Updated weights for policy 0, policy_version 1460 (0.0007)
|
| 390 |
+
[2024-11-12 19:55:42,606][4080811] Updated weights for policy 0, policy_version 1470 (0.0006)
|
| 391 |
+
[2024-11-12 19:55:43,928][4080811] Updated weights for policy 0, policy_version 1480 (0.0006)
|
| 392 |
+
[2024-11-12 19:55:45,255][4080811] Updated weights for policy 0, policy_version 1490 (0.0006)
|
| 393 |
+
[2024-11-12 19:55:45,321][4080366] Fps is (10 sec: 31129.5, 60 sec: 31470.9, 300 sec: 30515.3). Total num frames: 6103040. Throughput: 0: 7862.3. Samples: 1508594. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
| 394 |
+
[2024-11-12 19:55:45,322][4080366] Avg episode reward: [(0, '28.179')]
|
| 395 |
+
[2024-11-12 19:55:45,322][4080798] Saving new best policy, reward=28.179!
|
| 396 |
+
[2024-11-12 19:55:46,529][4080811] Updated weights for policy 0, policy_version 1500 (0.0007)
|
| 397 |
+
[2024-11-12 19:55:47,851][4080811] Updated weights for policy 0, policy_version 1510 (0.0007)
|
| 398 |
+
[2024-11-12 19:55:49,121][4080811] Updated weights for policy 0, policy_version 1520 (0.0007)
|
| 399 |
+
[2024-11-12 19:55:50,321][4080366] Fps is (10 sec: 31539.8, 60 sec: 31539.3, 300 sec: 30550.2). Total num frames: 6262784. Throughput: 0: 7844.0. Samples: 1555602. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 400 |
+
[2024-11-12 19:55:50,322][4080366] Avg episode reward: [(0, '21.492')]
|
| 401 |
+
[2024-11-12 19:55:50,440][4080811] Updated weights for policy 0, policy_version 1530 (0.0007)
|
| 402 |
+
[2024-11-12 19:55:51,748][4080811] Updated weights for policy 0, policy_version 1540 (0.0007)
|
| 403 |
+
[2024-11-12 19:55:53,031][4080811] Updated weights for policy 0, policy_version 1550 (0.0007)
|
| 404 |
+
[2024-11-12 19:55:54,350][4080811] Updated weights for policy 0, policy_version 1560 (0.0008)
|
| 405 |
+
[2024-11-12 19:55:55,321][4080366] Fps is (10 sec: 31538.7, 60 sec: 31402.7, 300 sec: 30564.0). Total num frames: 6418432. Throughput: 0: 7852.9. Samples: 1602972. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
|
| 406 |
+
[2024-11-12 19:55:55,322][4080366] Avg episode reward: [(0, '24.670')]
|
| 407 |
+
[2024-11-12 19:55:55,614][4080811] Updated weights for policy 0, policy_version 1570 (0.0007)
|
| 408 |
+
[2024-11-12 19:55:56,939][4080811] Updated weights for policy 0, policy_version 1580 (0.0006)
|
| 409 |
+
[2024-11-12 19:55:58,251][4080811] Updated weights for policy 0, policy_version 1590 (0.0008)
|
| 410 |
+
[2024-11-12 19:55:59,514][4080811] Updated weights for policy 0, policy_version 1600 (0.0006)
|
| 411 |
+
[2024-11-12 19:56:00,321][4080366] Fps is (10 sec: 31539.0, 60 sec: 31471.0, 300 sec: 30596.2). Total num frames: 6578176. Throughput: 0: 7860.6. Samples: 1626618. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0)
|
| 412 |
+
[2024-11-12 19:56:00,322][4080366] Avg episode reward: [(0, '25.765')]
|
| 413 |
+
[2024-11-12 19:56:00,806][4080811] Updated weights for policy 0, policy_version 1610 (0.0007)
|
| 414 |
+
[2024-11-12 19:56:02,064][4080811] Updated weights for policy 0, policy_version 1620 (0.0007)
|
| 415 |
+
[2024-11-12 19:56:03,347][4080811] Updated weights for policy 0, policy_version 1630 (0.0007)
|
| 416 |
+
[2024-11-12 19:56:04,649][4080811] Updated weights for policy 0, policy_version 1640 (0.0007)
|
| 417 |
+
[2024-11-12 19:56:05,321][4080366] Fps is (10 sec: 31948.1, 60 sec: 31470.8, 300 sec: 30626.9). Total num frames: 6737920. Throughput: 0: 7869.8. Samples: 1674572. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 418 |
+
[2024-11-12 19:56:05,323][4080366] Avg episode reward: [(0, '25.263')]
|
| 419 |
+
[2024-11-12 19:56:05,945][4080811] Updated weights for policy 0, policy_version 1650 (0.0008)
|
| 420 |
+
[2024-11-12 19:56:07,254][4080811] Updated weights for policy 0, policy_version 1660 (0.0007)
|
| 421 |
+
[2024-11-12 19:56:08,561][4080811] Updated weights for policy 0, policy_version 1670 (0.0006)
|
| 422 |
+
[2024-11-12 19:56:09,851][4080811] Updated weights for policy 0, policy_version 1680 (0.0007)
|
| 423 |
+
[2024-11-12 19:56:10,321][4080366] Fps is (10 sec: 31539.4, 60 sec: 31470.9, 300 sec: 30638.2). Total num frames: 6893568. Throughput: 0: 7862.1. Samples: 1721640. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 424 |
+
[2024-11-12 19:56:10,322][4080366] Avg episode reward: [(0, '22.771')]
|
| 425 |
+
[2024-11-12 19:56:11,208][4080811] Updated weights for policy 0, policy_version 1690 (0.0007)
|
| 426 |
+
[2024-11-12 19:56:12,536][4080811] Updated weights for policy 0, policy_version 1700 (0.0007)
|
| 427 |
+
[2024-11-12 19:56:13,858][4080811] Updated weights for policy 0, policy_version 1710 (0.0007)
|
| 428 |
+
[2024-11-12 19:56:15,150][4080811] Updated weights for policy 0, policy_version 1720 (0.0007)
|
| 429 |
+
[2024-11-12 19:56:15,321][4080366] Fps is (10 sec: 31130.5, 60 sec: 31471.1, 300 sec: 30648.8). Total num frames: 7049216. Throughput: 0: 7850.2. Samples: 1744686. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
| 430 |
+
[2024-11-12 19:56:15,322][4080366] Avg episode reward: [(0, '26.287')]
|
| 431 |
+
[2024-11-12 19:56:16,466][4080811] Updated weights for policy 0, policy_version 1730 (0.0007)
|
| 432 |
+
[2024-11-12 19:56:17,754][4080811] Updated weights for policy 0, policy_version 1740 (0.0007)
|
| 433 |
+
[2024-11-12 19:56:19,056][4080811] Updated weights for policy 0, policy_version 1750 (0.0007)
|
| 434 |
+
[2024-11-12 19:56:20,321][4080366] Fps is (10 sec: 30719.3, 60 sec: 31334.3, 300 sec: 30641.6). Total num frames: 7200768. Throughput: 0: 7853.4. Samples: 1791816. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0)
|
| 435 |
+
[2024-11-12 19:56:20,323][4080366] Avg episode reward: [(0, '22.495')]
|
| 436 |
+
[2024-11-12 19:56:20,327][4080798] Saving /media/kemove/17a64fef-179c-4620-a965-511df0584b38/home/yunpeng/transformers/deep-rl-class-main/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000001758_7200768.pth...
|
| 437 |
+
[2024-11-12 19:56:20,568][4080811] Updated weights for policy 0, policy_version 1760 (0.0008)
|
| 438 |
+
[2024-11-12 19:56:21,938][4080811] Updated weights for policy 0, policy_version 1770 (0.0006)
|
| 439 |
+
[2024-11-12 19:56:23,176][4080811] Updated weights for policy 0, policy_version 1780 (0.0005)
|
| 440 |
+
[2024-11-12 19:56:24,457][4080811] Updated weights for policy 0, policy_version 1790 (0.0006)
|
| 441 |
+
[2024-11-12 19:56:25,321][4080366] Fps is (10 sec: 31128.9, 60 sec: 31334.3, 300 sec: 30668.8). Total num frames: 7360512. Throughput: 0: 7845.4. Samples: 1838128. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
| 442 |
+
[2024-11-12 19:56:25,323][4080366] Avg episode reward: [(0, '22.629')]
|
| 443 |
+
[2024-11-12 19:56:25,604][4080811] Updated weights for policy 0, policy_version 1800 (0.0005)
|
| 444 |
+
[2024-11-12 19:56:26,790][4080811] Updated weights for policy 0, policy_version 1810 (0.0005)
|
| 445 |
+
[2024-11-12 19:56:27,987][4080811] Updated weights for policy 0, policy_version 1820 (0.0005)
|
| 446 |
+
[2024-11-12 19:56:29,154][4080811] Updated weights for policy 0, policy_version 1830 (0.0005)
|
| 447 |
+
[2024-11-12 19:56:30,298][4080811] Updated weights for policy 0, policy_version 1840 (0.0005)
|
| 448 |
+
[2024-11-12 19:56:30,321][4080366] Fps is (10 sec: 33586.9, 60 sec: 31675.6, 300 sec: 30761.8). Total num frames: 7536640. Throughput: 0: 7897.6. Samples: 1863986. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 449 |
+
[2024-11-12 19:56:30,323][4080366] Avg episode reward: [(0, '24.512')]
|
| 450 |
+
[2024-11-12 19:56:31,516][4080811] Updated weights for policy 0, policy_version 1850 (0.0006)
|
| 451 |
+
[2024-11-12 19:56:32,677][4080811] Updated weights for policy 0, policy_version 1860 (0.0005)
|
| 452 |
+
[2024-11-12 19:56:33,829][4080811] Updated weights for policy 0, policy_version 1870 (0.0005)
|
| 453 |
+
[2024-11-12 19:56:35,067][4080811] Updated weights for policy 0, policy_version 1880 (0.0005)
|
| 454 |
+
[2024-11-12 19:56:35,321][4080366] Fps is (10 sec: 34816.2, 60 sec: 31948.7, 300 sec: 30834.7). Total num frames: 7708672. Throughput: 0: 8019.2. Samples: 1916466. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
| 455 |
+
[2024-11-12 19:56:35,322][4080366] Avg episode reward: [(0, '21.457')]
|
| 456 |
+
[2024-11-12 19:56:36,268][4080811] Updated weights for policy 0, policy_version 1890 (0.0005)
|
| 457 |
+
[2024-11-12 19:56:37,412][4080811] Updated weights for policy 0, policy_version 1900 (0.0005)
|
| 458 |
+
[2024-11-12 19:56:38,596][4080811] Updated weights for policy 0, policy_version 1910 (0.0006)
|
| 459 |
+
[2024-11-12 19:56:39,803][4080811] Updated weights for policy 0, policy_version 1920 (0.0006)
|
| 460 |
+
[2024-11-12 19:56:40,321][4080366] Fps is (10 sec: 34407.6, 60 sec: 32222.0, 300 sec: 30904.8). Total num frames: 7880704. Throughput: 0: 8111.2. Samples: 1967976. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
| 461 |
+
[2024-11-12 19:56:40,322][4080366] Avg episode reward: [(0, '26.030')]
|
| 462 |
+
[2024-11-12 19:56:40,995][4080811] Updated weights for policy 0, policy_version 1930 (0.0006)
|
| 463 |
+
[2024-11-12 19:56:42,161][4080811] Updated weights for policy 0, policy_version 1940 (0.0005)
|
| 464 |
+
[2024-11-12 19:56:43,354][4080811] Updated weights for policy 0, policy_version 1950 (0.0006)
|
| 465 |
+
[2024-11-12 19:56:43,960][4080798] Stopping Batcher_0...
|
| 466 |
+
[2024-11-12 19:56:43,961][4080798] Loop batcher_evt_loop terminating...
|
| 467 |
+
[2024-11-12 19:56:43,960][4080366] Component Batcher_0 stopped!
|
| 468 |
+
[2024-11-12 19:56:43,961][4080798] Saving /media/kemove/17a64fef-179c-4620-a965-511df0584b38/home/yunpeng/transformers/deep-rl-class-main/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000001955_8007680.pth...
|
| 469 |
+
[2024-11-12 19:56:43,962][4080366] Component RolloutWorker_w0 process died already! Don't wait for it.
|
| 470 |
+
[2024-11-12 19:56:43,962][4080366] Component RolloutWorker_w2 process died already! Don't wait for it.
|
| 471 |
+
[2024-11-12 19:56:43,987][4080811] Weights refcount: 2 0
|
| 472 |
+
[2024-11-12 19:56:43,989][4080811] Stopping InferenceWorker_p0-w0...
|
| 473 |
+
[2024-11-12 19:56:43,990][4080811] Loop inference_proc0-0_evt_loop terminating...
|
| 474 |
+
[2024-11-12 19:56:43,990][4080366] Component InferenceWorker_p0-w0 stopped!
|
| 475 |
+
[2024-11-12 19:56:43,999][4080815] Stopping RolloutWorker_w3...
|
| 476 |
+
[2024-11-12 19:56:43,999][4080812] Stopping RolloutWorker_w1...
|
| 477 |
+
[2024-11-12 19:56:44,000][4080815] Loop rollout_proc3_evt_loop terminating...
|
| 478 |
+
[2024-11-12 19:56:44,000][4080812] Loop rollout_proc1_evt_loop terminating...
|
| 479 |
+
[2024-11-12 19:56:44,000][4080817] Stopping RolloutWorker_w4...
|
| 480 |
+
[2024-11-12 19:56:44,000][4080819] Stopping RolloutWorker_w7...
|
| 481 |
+
[2024-11-12 19:56:44,000][4080818] Stopping RolloutWorker_w6...
|
| 482 |
+
[2024-11-12 19:56:44,001][4080819] Loop rollout_proc7_evt_loop terminating...
|
| 483 |
+
[2024-11-12 19:56:44,001][4080817] Loop rollout_proc4_evt_loop terminating...
|
| 484 |
+
[2024-11-12 19:56:44,001][4080816] Stopping RolloutWorker_w5...
|
| 485 |
+
[2024-11-12 19:56:44,001][4080818] Loop rollout_proc6_evt_loop terminating...
|
| 486 |
+
[2024-11-12 19:56:44,001][4080816] Loop rollout_proc5_evt_loop terminating...
|
| 487 |
+
[2024-11-12 19:56:43,999][4080366] Component RolloutWorker_w3 stopped!
|
| 488 |
+
[2024-11-12 19:56:44,002][4080366] Component RolloutWorker_w1 stopped!
|
| 489 |
+
[2024-11-12 19:56:44,003][4080366] Component RolloutWorker_w4 stopped!
|
| 490 |
+
[2024-11-12 19:56:44,003][4080366] Component RolloutWorker_w7 stopped!
|
| 491 |
+
[2024-11-12 19:56:44,004][4080366] Component RolloutWorker_w6 stopped!
|
| 492 |
+
[2024-11-12 19:56:44,005][4080366] Component RolloutWorker_w5 stopped!
|
| 493 |
+
[2024-11-12 19:56:44,046][4080798] Removing /media/kemove/17a64fef-179c-4620-a965-511df0584b38/home/yunpeng/transformers/deep-rl-class-main/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000836_3424256.pth
|
| 494 |
+
[2024-11-12 19:56:44,057][4080798] Saving /media/kemove/17a64fef-179c-4620-a965-511df0584b38/home/yunpeng/transformers/deep-rl-class-main/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000001955_8007680.pth...
|
| 495 |
+
[2024-11-12 19:56:44,488][4080798] Stopping LearnerWorker_p0...
|
| 496 |
+
[2024-11-12 19:56:44,489][4080798] Loop learner_proc0_evt_loop terminating...
|
| 497 |
+
[2024-11-12 19:56:44,489][4080366] Component LearnerWorker_p0 stopped!
|
| 498 |
+
[2024-11-12 19:56:44,490][4080366] Waiting for process learner_proc0 to stop...
|
| 499 |
+
[2024-11-12 19:56:45,109][4080366] Waiting for process inference_proc0-0 to join...
|
| 500 |
+
[2024-11-12 19:56:45,110][4080366] Waiting for process rollout_proc0 to join...
|
| 501 |
+
[2024-11-12 19:56:45,110][4080366] Waiting for process rollout_proc1 to join...
|
| 502 |
+
[2024-11-12 19:56:45,111][4080366] Waiting for process rollout_proc2 to join...
|
| 503 |
+
[2024-11-12 19:56:45,111][4080366] Waiting for process rollout_proc3 to join...
|
| 504 |
+
[2024-11-12 19:56:45,111][4080366] Waiting for process rollout_proc4 to join...
|
| 505 |
+
[2024-11-12 19:56:45,111][4080366] Waiting for process rollout_proc5 to join...
|
| 506 |
+
[2024-11-12 19:56:45,111][4080366] Waiting for process rollout_proc6 to join...
|
| 507 |
+
[2024-11-12 19:56:45,112][4080366] Waiting for process rollout_proc7 to join...
|
| 508 |
+
[2024-11-12 19:56:45,112][4080366] Batcher 0 profile tree view:
|
| 509 |
+
batching: 26.9027, releasing_batches: 0.0357
|
| 510 |
+
[2024-11-12 19:56:45,112][4080366] InferenceWorker_p0-w0 profile tree view:
|
| 511 |
+
wait_policy: 0.0000
|
| 512 |
+
wait_policy_total: 3.7839
|
| 513 |
+
update_model: 3.9104
|
| 514 |
+
weight_update: 0.0005
|
| 515 |
+
one_step: 0.0020
|
| 516 |
+
handle_policy_step: 233.9468
|
| 517 |
+
deserialize: 12.5786, stack: 1.3074, obs_to_device_normalize: 59.5991, forward: 114.8215, send_messages: 10.9577
|
| 518 |
+
prepare_outputs: 25.3487
|
| 519 |
+
to_cpu: 14.6066
|
| 520 |
+
[2024-11-12 19:56:45,112][4080366] Learner 0 profile tree view:
|
| 521 |
+
misc: 0.0097, prepare_batch: 9.7770
|
| 522 |
+
train: 26.0776
|
| 523 |
+
epoch_init: 0.0065, minibatch_init: 0.0074, losses_postprocess: 0.6240, kl_divergence: 0.5407, after_optimizer: 6.5999
|
| 524 |
+
calculate_losses: 9.5364
|
| 525 |
+
losses_init: 0.0028, forward_head: 0.7589, bptt_initial: 5.6054, tail: 0.6684, advantages_returns: 0.1629, losses: 0.9611
|
| 526 |
+
bptt: 1.2044
|
| 527 |
+
bptt_forward_core: 1.1543
|
| 528 |
+
update: 8.3829
|
| 529 |
+
clip: 0.6208
|
| 530 |
+
[2024-11-12 19:56:45,113][4080366] RolloutWorker_w7 profile tree view:
|
| 531 |
+
wait_for_trajectories: 0.2070, enqueue_policy_requests: 10.1650, env_step: 142.2907, overhead: 12.2160, complete_rollouts: 0.3404
|
| 532 |
+
save_policy_outputs: 10.5431
|
| 533 |
+
split_output_tensors: 4.9354
|
| 534 |
+
[2024-11-12 19:56:45,113][4080366] Loop Runner_EvtLoop terminating...
|
| 535 |
+
[2024-11-12 19:56:45,113][4080366] Runner profile tree view:
|
| 536 |
+
main_loop: 263.5364
|
| 537 |
+
[2024-11-12 19:56:45,113][4080366] Collected {0: 8007680}, FPS: 30385.5
|
| 538 |
+
[2024-11-12 19:57:53,988][4080366] Loading existing experiment configuration from /media/kemove/17a64fef-179c-4620-a965-511df0584b38/home/yunpeng/transformers/deep-rl-class-main/notebooks/unit8/train_dir/default_experiment/config.json
|
| 539 |
+
[2024-11-12 19:57:53,988][4080366] Overriding arg 'num_workers' with value 1 passed from command line
|
| 540 |
+
[2024-11-12 19:57:53,989][4080366] Adding new argument 'no_render'=True that is not in the saved config file!
|
| 541 |
+
[2024-11-12 19:57:53,989][4080366] Adding new argument 'save_video'=True that is not in the saved config file!
|
| 542 |
+
[2024-11-12 19:57:53,989][4080366] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
|
| 543 |
+
[2024-11-12 19:57:53,989][4080366] Adding new argument 'video_name'=None that is not in the saved config file!
|
| 544 |
+
[2024-11-12 19:57:53,990][4080366] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
|
| 545 |
+
[2024-11-12 19:57:53,990][4080366] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
|
| 546 |
+
[2024-11-12 19:57:53,990][4080366] Adding new argument 'push_to_hub'=False that is not in the saved config file!
|
| 547 |
+
[2024-11-12 19:57:53,990][4080366] Adding new argument 'hf_repository'=None that is not in the saved config file!
|
| 548 |
+
[2024-11-12 19:57:53,990][4080366] Adding new argument 'policy_index'=0 that is not in the saved config file!
|
| 549 |
+
[2024-11-12 19:57:53,991][4080366] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
|
| 550 |
+
[2024-11-12 19:57:53,991][4080366] Adding new argument 'train_script'=None that is not in the saved config file!
|
| 551 |
+
[2024-11-12 19:57:53,991][4080366] Adding new argument 'enjoy_script'=None that is not in the saved config file!
|
| 552 |
+
[2024-11-12 19:57:53,991][4080366] Using frameskip 1 and render_action_repeat=4 for evaluation
|
| 553 |
+
[2024-11-12 19:57:54,005][4080366] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 554 |
+
[2024-11-12 19:57:54,007][4080366] RunningMeanStd input shape: (3, 72, 128)
|
| 555 |
+
[2024-11-12 19:57:54,008][4080366] RunningMeanStd input shape: (1,)
|
| 556 |
+
[2024-11-12 19:57:54,013][4080366] ConvEncoder: input_channels=3
|
| 557 |
+
[2024-11-12 19:57:54,079][4080366] Conv encoder output size: 512
|
| 558 |
+
[2024-11-12 19:57:54,079][4080366] Policy head output size: 512
|
| 559 |
+
[2024-11-12 19:57:54,176][4080366] Loading state from checkpoint /media/kemove/17a64fef-179c-4620-a965-511df0584b38/home/yunpeng/transformers/deep-rl-class-main/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000001955_8007680.pth...
|
| 560 |
+
[2024-11-12 19:57:54,892][4080366] Num frames 100...
|
| 561 |
+
[2024-11-12 19:57:54,939][4080366] Num frames 200...
|
| 562 |
+
[2024-11-12 19:57:54,997][4080366] Num frames 300...
|
| 563 |
+
[2024-11-12 19:57:55,045][4080366] Num frames 400...
|
| 564 |
+
[2024-11-12 19:57:55,096][4080366] Num frames 500...
|
| 565 |
+
[2024-11-12 19:57:55,141][4080366] Num frames 600...
|
| 566 |
+
[2024-11-12 19:57:55,183][4080366] Num frames 700...
|
| 567 |
+
[2024-11-12 19:57:55,228][4080366] Num frames 800...
|
| 568 |
+
[2024-11-12 19:57:55,308][4080366] Avg episode rewards: #0: 24.640, true rewards: #0: 8.640
|
| 569 |
+
[2024-11-12 19:57:55,310][4080366] Avg episode reward: 24.640, avg true_objective: 8.640
|
| 570 |
+
[2024-11-12 19:57:55,370][4080366] Num frames 900...
|
| 571 |
+
[2024-11-12 19:57:55,417][4080366] Num frames 1000...
|
| 572 |
+
[2024-11-12 19:57:55,461][4080366] Num frames 1100...
|
| 573 |
+
[2024-11-12 19:57:55,505][4080366] Num frames 1200...
|
| 574 |
+
[2024-11-12 19:57:55,549][4080366] Num frames 1300...
|
| 575 |
+
[2024-11-12 19:57:55,591][4080366] Num frames 1400...
|
| 576 |
+
[2024-11-12 19:57:55,632][4080366] Num frames 1500...
|
| 577 |
+
[2024-11-12 19:57:55,674][4080366] Num frames 1600...
|
| 578 |
+
[2024-11-12 19:57:55,716][4080366] Num frames 1700...
|
| 579 |
+
[2024-11-12 19:57:55,763][4080366] Num frames 1800...
|
| 580 |
+
[2024-11-12 19:57:55,806][4080366] Num frames 1900...
|
| 581 |
+
[2024-11-12 19:57:55,849][4080366] Num frames 2000...
|
| 582 |
+
[2024-11-12 19:57:55,895][4080366] Num frames 2100...
|
| 583 |
+
[2024-11-12 19:57:55,941][4080366] Num frames 2200...
|
| 584 |
+
[2024-11-12 19:57:55,992][4080366] Num frames 2300...
|
| 585 |
+
[2024-11-12 19:57:56,071][4080366] Num frames 2400...
|
| 586 |
+
[2024-11-12 19:57:56,122][4080366] Avg episode rewards: #0: 28.000, true rewards: #0: 12.000
|
| 587 |
+
[2024-11-12 19:57:56,124][4080366] Avg episode reward: 28.000, avg true_objective: 12.000
|
| 588 |
+
[2024-11-12 19:57:56,195][4080366] Num frames 2500...
|
| 589 |
+
[2024-11-12 19:57:56,242][4080366] Num frames 2600...
|
| 590 |
+
[2024-11-12 19:57:56,307][4080366] Num frames 2700...
|
| 591 |
+
[2024-11-12 19:57:56,377][4080366] Num frames 2800...
|
| 592 |
+
[2024-11-12 19:57:56,424][4080366] Num frames 2900...
|
| 593 |
+
[2024-11-12 19:57:56,474][4080366] Num frames 3000...
|
| 594 |
+
[2024-11-12 19:57:56,520][4080366] Num frames 3100...
|
| 595 |
+
[2024-11-12 19:57:56,566][4080366] Num frames 3200...
|
| 596 |
+
[2024-11-12 19:57:56,644][4080366] Avg episode rewards: #0: 25.107, true rewards: #0: 10.773
|
| 597 |
+
[2024-11-12 19:57:56,645][4080366] Avg episode reward: 25.107, avg true_objective: 10.773
|
| 598 |
+
[2024-11-12 19:57:56,688][4080366] Num frames 3300...
|
| 599 |
+
[2024-11-12 19:57:56,741][4080366] Num frames 3400...
|
| 600 |
+
[2024-11-12 19:57:56,786][4080366] Num frames 3500...
|
| 601 |
+
[2024-11-12 19:57:56,840][4080366] Num frames 3600...
|
| 602 |
+
[2024-11-12 19:57:56,888][4080366] Num frames 3700...
|
| 603 |
+
[2024-11-12 19:57:56,936][4080366] Num frames 3800...
|
| 604 |
+
[2024-11-12 19:57:56,982][4080366] Num frames 3900...
|
| 605 |
+
[2024-11-12 19:57:57,039][4080366] Avg episode rewards: #0: 23.010, true rewards: #0: 9.760
|
| 606 |
+
[2024-11-12 19:57:57,041][4080366] Avg episode reward: 23.010, avg true_objective: 9.760
|
| 607 |
+
[2024-11-12 19:57:57,144][4080366] Num frames 4000...
|
| 608 |
+
[2024-11-12 19:57:57,197][4080366] Num frames 4100...
|
| 609 |
+
[2024-11-12 19:57:57,243][4080366] Num frames 4200...
|
| 610 |
+
[2024-11-12 19:57:57,303][4080366] Num frames 4300...
|
| 611 |
+
[2024-11-12 19:57:57,354][4080366] Num frames 4400...
|
| 612 |
+
[2024-11-12 19:57:57,398][4080366] Num frames 4500...
|
| 613 |
+
[2024-11-12 19:57:57,443][4080366] Num frames 4600...
|
| 614 |
+
[2024-11-12 19:57:57,491][4080366] Num frames 4700...
|
| 615 |
+
[2024-11-12 19:57:57,535][4080366] Num frames 4800...
|
| 616 |
+
[2024-11-12 19:57:57,579][4080366] Num frames 4900...
|
| 617 |
+
[2024-11-12 19:57:57,623][4080366] Num frames 5000...
|
| 618 |
+
[2024-11-12 19:57:57,673][4080366] Num frames 5100...
|
| 619 |
+
[2024-11-12 19:57:57,734][4080366] Avg episode rewards: #0: 23.640, true rewards: #0: 10.240
|
| 620 |
+
[2024-11-12 19:57:57,739][4080366] Avg episode reward: 23.640, avg true_objective: 10.240
|
| 621 |
+
[2024-11-12 19:57:57,797][4080366] Num frames 5200...
|
| 622 |
+
[2024-11-12 19:57:57,838][4080366] Num frames 5300...
|
| 623 |
+
[2024-11-12 19:57:57,884][4080366] Num frames 5400...
|
| 624 |
+
[2024-11-12 19:57:57,963][4080366] Num frames 5500...
|
| 625 |
+
[2024-11-12 19:57:58,016][4080366] Num frames 5600...
|
| 626 |
+
[2024-11-12 19:57:58,096][4080366] Avg episode rewards: #0: 21.607, true rewards: #0: 9.440
|
| 627 |
+
[2024-11-12 19:57:58,099][4080366] Avg episode reward: 21.607, avg true_objective: 9.440
|
| 628 |
+
[2024-11-12 19:57:58,136][4080366] Num frames 5700...
|
| 629 |
+
[2024-11-12 19:57:58,181][4080366] Num frames 5800...
|
| 630 |
+
[2024-11-12 19:57:58,230][4080366] Num frames 5900...
|
| 631 |
+
[2024-11-12 19:57:58,273][4080366] Num frames 6000...
|
| 632 |
+
[2024-11-12 19:57:58,317][4080366] Num frames 6100...
|
| 633 |
+
[2024-11-12 19:57:58,361][4080366] Num frames 6200...
|
| 634 |
+
[2024-11-12 19:57:58,406][4080366] Num frames 6300...
|
| 635 |
+
[2024-11-12 19:57:58,450][4080366] Num frames 6400...
|
| 636 |
+
[2024-11-12 19:57:58,497][4080366] Num frames 6500...
|
| 637 |
+
[2024-11-12 19:57:58,544][4080366] Num frames 6600...
|
| 638 |
+
[2024-11-12 19:57:58,590][4080366] Num frames 6700...
|
| 639 |
+
[2024-11-12 19:57:58,635][4080366] Num frames 6800...
|
| 640 |
+
[2024-11-12 19:57:58,679][4080366] Num frames 6900...
|
| 641 |
+
[2024-11-12 19:57:58,724][4080366] Num frames 7000...
|
| 642 |
+
[2024-11-12 19:57:58,766][4080366] Num frames 7100...
|
| 643 |
+
[2024-11-12 19:57:58,807][4080366] Num frames 7200...
|
| 644 |
+
[2024-11-12 19:57:58,875][4080366] Avg episode rewards: #0: 24.046, true rewards: #0: 10.331
|
| 645 |
+
[2024-11-12 19:57:58,877][4080366] Avg episode reward: 24.046, avg true_objective: 10.331
|
| 646 |
+
[2024-11-12 19:57:58,932][4080366] Num frames 7300...
|
| 647 |
+
[2024-11-12 19:57:58,981][4080366] Num frames 7400...
|
| 648 |
+
[2024-11-12 19:57:59,038][4080366] Num frames 7500...
|
| 649 |
+
[2024-11-12 19:57:59,082][4080366] Num frames 7600...
|
| 650 |
+
[2024-11-12 19:57:59,125][4080366] Num frames 7700...
|
| 651 |
+
[2024-11-12 19:57:59,168][4080366] Num frames 7800...
|
| 652 |
+
[2024-11-12 19:57:59,228][4080366] Num frames 7900...
|
| 653 |
+
[2024-11-12 19:57:59,270][4080366] Num frames 8000...
|
| 654 |
+
[2024-11-12 19:57:59,314][4080366] Num frames 8100...
|
| 655 |
+
[2024-11-12 19:57:59,360][4080366] Num frames 8200...
|
| 656 |
+
[2024-11-12 19:57:59,406][4080366] Num frames 8300...
|
| 657 |
+
[2024-11-12 19:57:59,451][4080366] Num frames 8400...
|
| 658 |
+
[2024-11-12 19:57:59,524][4080366] Avg episode rewards: #0: 24.935, true rewards: #0: 10.560
|
| 659 |
+
[2024-11-12 19:57:59,526][4080366] Avg episode reward: 24.935, avg true_objective: 10.560
|
| 660 |
+
[2024-11-12 19:57:59,571][4080366] Num frames 8500...
|
| 661 |
+
[2024-11-12 19:57:59,615][4080366] Num frames 8600...
|
| 662 |
+
[2024-11-12 19:57:59,659][4080366] Num frames 8700...
|
| 663 |
+
[2024-11-12 19:57:59,702][4080366] Num frames 8800...
|
| 664 |
+
[2024-11-12 19:57:59,750][4080366] Num frames 8900...
|
| 665 |
+
[2024-11-12 19:57:59,796][4080366] Num frames 9000...
|
| 666 |
+
[2024-11-12 19:57:59,841][4080366] Num frames 9100...
|
| 667 |
+
[2024-11-12 19:57:59,884][4080366] Num frames 9200...
|
| 668 |
+
[2024-11-12 19:57:59,932][4080366] Num frames 9300...
|
| 669 |
+
[2024-11-12 19:57:59,993][4080366] Num frames 9400...
|
| 670 |
+
[2024-11-12 19:58:00,057][4080366] Num frames 9500...
|
| 671 |
+
[2024-11-12 19:58:00,105][4080366] Num frames 9600...
|
| 672 |
+
[2024-11-12 19:58:00,185][4080366] Avg episode rewards: #0: 25.288, true rewards: #0: 10.732
|
| 673 |
+
[2024-11-12 19:58:00,187][4080366] Avg episode reward: 25.288, avg true_objective: 10.732
|
| 674 |
+
[2024-11-12 19:58:00,224][4080366] Num frames 9700...
|
| 675 |
+
[2024-11-12 19:58:00,268][4080366] Num frames 9800...
|
| 676 |
+
[2024-11-12 19:58:00,329][4080366] Avg episode rewards: #0: 23.019, true rewards: #0: 9.819
|
| 677 |
+
[2024-11-12 19:58:00,331][4080366] Avg episode reward: 23.019, avg true_objective: 9.819
|
| 678 |
+
[2024-11-12 19:58:10,093][4080366] Replay video saved to /media/kemove/17a64fef-179c-4620-a965-511df0584b38/home/yunpeng/transformers/deep-rl-class-main/notebooks/unit8/train_dir/default_experiment/replay.mp4!
|
| 679 |
+
[2024-11-12 20:00:58,329][4080366] Loading existing experiment configuration from /media/kemove/17a64fef-179c-4620-a965-511df0584b38/home/yunpeng/transformers/deep-rl-class-main/notebooks/unit8/train_dir/default_experiment/config.json
|
| 680 |
+
[2024-11-12 20:00:58,330][4080366] Overriding arg 'num_workers' with value 1 passed from command line
|
| 681 |
+
[2024-11-12 20:00:58,331][4080366] Adding new argument 'no_render'=True that is not in the saved config file!
|
| 682 |
+
[2024-11-12 20:00:58,332][4080366] Adding new argument 'save_video'=True that is not in the saved config file!
|
| 683 |
+
[2024-11-12 20:00:58,332][4080366] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
|
| 684 |
+
[2024-11-12 20:00:58,333][4080366] Adding new argument 'video_name'=None that is not in the saved config file!
|
| 685 |
+
[2024-11-12 20:00:58,333][4080366] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
|
| 686 |
+
[2024-11-12 20:00:58,334][4080366] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
|
| 687 |
+
[2024-11-12 20:00:58,334][4080366] Adding new argument 'push_to_hub'=True that is not in the saved config file!
|
| 688 |
+
[2024-11-12 20:00:58,335][4080366] Adding new argument 'hf_repository'='sun-s/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
|
| 689 |
+
[2024-11-12 20:00:58,336][4080366] Adding new argument 'policy_index'=0 that is not in the saved config file!
|
| 690 |
+
[2024-11-12 20:00:58,336][4080366] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
|
| 691 |
+
[2024-11-12 20:00:58,337][4080366] Adding new argument 'train_script'=None that is not in the saved config file!
|
| 692 |
+
[2024-11-12 20:00:58,338][4080366] Adding new argument 'enjoy_script'=None that is not in the saved config file!
|
| 693 |
+
[2024-11-12 20:00:58,338][4080366] Using frameskip 1 and render_action_repeat=4 for evaluation
|
| 694 |
+
[2024-11-12 20:00:58,358][4080366] RunningMeanStd input shape: (3, 72, 128)
|
| 695 |
+
[2024-11-12 20:00:58,359][4080366] RunningMeanStd input shape: (1,)
|
| 696 |
+
[2024-11-12 20:00:58,365][4080366] ConvEncoder: input_channels=3
|
| 697 |
+
[2024-11-12 20:00:58,395][4080366] Conv encoder output size: 512
|
| 698 |
+
[2024-11-12 20:00:58,396][4080366] Policy head output size: 512
|
| 699 |
+
[2024-11-12 20:00:58,425][4080366] Loading state from checkpoint /media/kemove/17a64fef-179c-4620-a965-511df0584b38/home/yunpeng/transformers/deep-rl-class-main/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000001955_8007680.pth...
|
| 700 |
+
[2024-11-12 20:00:58,917][4080366] Num frames 100...
|
| 701 |
+
[2024-11-12 20:00:58,973][4080366] Num frames 200...
|
| 702 |
+
[2024-11-12 20:00:59,030][4080366] Num frames 300...
|
| 703 |
+
[2024-11-12 20:00:59,082][4080366] Num frames 400...
|
| 704 |
+
[2024-11-12 20:00:59,140][4080366] Num frames 500...
|
| 705 |
+
[2024-11-12 20:00:59,197][4080366] Num frames 600...
|
| 706 |
+
[2024-11-12 20:00:59,249][4080366] Num frames 700...
|
| 707 |
+
[2024-11-12 20:00:59,306][4080366] Num frames 800...
|
| 708 |
+
[2024-11-12 20:00:59,362][4080366] Num frames 900...
|
| 709 |
+
[2024-11-12 20:00:59,415][4080366] Num frames 1000...
|
| 710 |
+
[2024-11-12 20:00:59,469][4080366] Num frames 1100...
|
| 711 |
+
[2024-11-12 20:00:59,518][4080366] Num frames 1200...
|
| 712 |
+
[2024-11-12 20:00:59,567][4080366] Num frames 1300...
|
| 713 |
+
[2024-11-12 20:00:59,619][4080366] Num frames 1400...
|
| 714 |
+
[2024-11-12 20:00:59,709][4080366] Avg episode rewards: #0: 40.760, true rewards: #0: 14.760
|
| 715 |
+
[2024-11-12 20:00:59,710][4080366] Avg episode reward: 40.760, avg true_objective: 14.760
|
| 716 |
+
[2024-11-12 20:00:59,721][4080366] Num frames 1500...
|
| 717 |
+
[2024-11-12 20:00:59,771][4080366] Num frames 1600...
|
| 718 |
+
[2024-11-12 20:00:59,815][4080366] Num frames 1700...
|
| 719 |
+
[2024-11-12 20:00:59,858][4080366] Num frames 1800...
|
| 720 |
+
[2024-11-12 20:00:59,923][4080366] Avg episode rewards: #0: 22.640, true rewards: #0: 9.140
|
| 721 |
+
[2024-11-12 20:00:59,925][4080366] Avg episode reward: 22.640, avg true_objective: 9.140
|
| 722 |
+
[2024-11-12 20:00:59,974][4080366] Num frames 1900...
|
| 723 |
+
[2024-11-12 20:01:00,020][4080366] Num frames 2000...
|
| 724 |
+
[2024-11-12 20:01:00,066][4080366] Num frames 2100...
|
| 725 |
+
[2024-11-12 20:01:00,108][4080366] Num frames 2200...
|
| 726 |
+
[2024-11-12 20:01:00,155][4080366] Num frames 2300...
|
| 727 |
+
[2024-11-12 20:01:00,205][4080366] Num frames 2400...
|
| 728 |
+
[2024-11-12 20:01:00,259][4080366] Num frames 2500...
|
| 729 |
+
[2024-11-12 20:01:00,303][4080366] Num frames 2600...
|
| 730 |
+
[2024-11-12 20:01:00,347][4080366] Num frames 2700...
|
| 731 |
+
[2024-11-12 20:01:00,391][4080366] Num frames 2800...
|
| 732 |
+
[2024-11-12 20:01:00,434][4080366] Num frames 2900...
|
| 733 |
+
[2024-11-12 20:01:00,477][4080366] Num frames 3000...
|
| 734 |
+
[2024-11-12 20:01:00,521][4080366] Num frames 3100...
|
| 735 |
+
[2024-11-12 20:01:00,572][4080366] Num frames 3200...
|
| 736 |
+
[2024-11-12 20:01:00,613][4080366] Num frames 3300...
|
| 737 |
+
[2024-11-12 20:01:00,654][4080366] Num frames 3400...
|
| 738 |
+
[2024-11-12 20:01:00,695][4080366] Num frames 3500...
|
| 739 |
+
[2024-11-12 20:01:00,737][4080366] Num frames 3600...
|
| 740 |
+
[2024-11-12 20:01:00,814][4080366] Avg episode rewards: #0: 30.160, true rewards: #0: 12.160
|
| 741 |
+
[2024-11-12 20:01:00,817][4080366] Avg episode reward: 30.160, avg true_objective: 12.160
|
| 742 |
+
[2024-11-12 20:01:00,892][4080366] Num frames 3700...
|
| 743 |
+
[2024-11-12 20:01:00,939][4080366] Num frames 3800...
|
| 744 |
+
[2024-11-12 20:01:00,985][4080366] Num frames 3900...
|
| 745 |
+
[2024-11-12 20:01:01,026][4080366] Num frames 4000...
|
| 746 |
+
[2024-11-12 20:01:01,095][4080366] Num frames 4100...
|
| 747 |
+
[2024-11-12 20:01:01,142][4080366] Num frames 4200...
|
| 748 |
+
[2024-11-12 20:01:01,189][4080366] Num frames 4300...
|
| 749 |
+
[2024-11-12 20:01:01,232][4080366] Num frames 4400...
|
| 750 |
+
[2024-11-12 20:01:01,315][4080366] Num frames 4500...
|
| 751 |
+
[2024-11-12 20:01:01,358][4080366] Num frames 4600...
|
| 752 |
+
[2024-11-12 20:01:01,400][4080366] Num frames 4700...
|
| 753 |
+
[2024-11-12 20:01:01,441][4080366] Num frames 4800...
|
| 754 |
+
[2024-11-12 20:01:01,507][4080366] Avg episode rewards: #0: 30.080, true rewards: #0: 12.080
|
| 755 |
+
[2024-11-12 20:01:01,509][4080366] Avg episode reward: 30.080, avg true_objective: 12.080
|
| 756 |
+
[2024-11-12 20:01:01,569][4080366] Num frames 4900...
|
| 757 |
+
[2024-11-12 20:01:01,611][4080366] Num frames 5000...
|
| 758 |
+
[2024-11-12 20:01:01,651][4080366] Num frames 5100...
|
| 759 |
+
[2024-11-12 20:01:01,693][4080366] Num frames 5200...
|
| 760 |
+
[2024-11-12 20:01:01,737][4080366] Num frames 5300...
|
| 761 |
+
[2024-11-12 20:01:01,779][4080366] Num frames 5400...
|
| 762 |
+
[2024-11-12 20:01:01,828][4080366] Num frames 5500...
|
| 763 |
+
[2024-11-12 20:01:01,895][4080366] Avg episode rewards: #0: 26.472, true rewards: #0: 11.072
|
| 764 |
+
[2024-11-12 20:01:01,896][4080366] Avg episode reward: 26.472, avg true_objective: 11.072
|
| 765 |
+
[2024-11-12 20:01:01,936][4080366] Num frames 5600...
|
| 766 |
+
[2024-11-12 20:01:01,977][4080366] Num frames 5700...
|
| 767 |
+
[2024-11-12 20:01:02,019][4080366] Num frames 5800...
|
| 768 |
+
[2024-11-12 20:01:02,061][4080366] Num frames 5900...
|
| 769 |
+
[2024-11-12 20:01:02,102][4080366] Num frames 6000...
|
| 770 |
+
[2024-11-12 20:01:02,149][4080366] Num frames 6100...
|
| 771 |
+
[2024-11-12 20:01:02,199][4080366] Num frames 6200...
|
| 772 |
+
[2024-11-12 20:01:02,259][4080366] Num frames 6300...
|
| 773 |
+
[2024-11-12 20:01:02,321][4080366] Avg episode rewards: #0: 24.703, true rewards: #0: 10.537
|
| 774 |
+
[2024-11-12 20:01:02,323][4080366] Avg episode reward: 24.703, avg true_objective: 10.537
|
| 775 |
+
[2024-11-12 20:01:02,369][4080366] Num frames 6400...
|
| 776 |
+
[2024-11-12 20:01:02,414][4080366] Num frames 6500...
|
| 777 |
+
[2024-11-12 20:01:02,456][4080366] Num frames 6600...
|
| 778 |
+
[2024-11-12 20:01:02,497][4080366] Num frames 6700...
|
| 779 |
+
[2024-11-12 20:01:02,538][4080366] Num frames 6800...
|
| 780 |
+
[2024-11-12 20:01:02,626][4080366] Avg episode rewards: #0: 22.551, true rewards: #0: 9.837
|
| 781 |
+
[2024-11-12 20:01:02,628][4080366] Avg episode reward: 22.551, avg true_objective: 9.837
|
| 782 |
+
[2024-11-12 20:01:02,653][4080366] Num frames 6900...
|
| 783 |
+
[2024-11-12 20:01:02,703][4080366] Num frames 7000...
|
| 784 |
+
[2024-11-12 20:01:02,746][4080366] Num frames 7100...
|
| 785 |
+
[2024-11-12 20:01:02,791][4080366] Num frames 7200...
|
| 786 |
+
[2024-11-12 20:01:02,835][4080366] Num frames 7300...
|
| 787 |
+
[2024-11-12 20:01:02,880][4080366] Num frames 7400...
|
| 788 |
+
[2024-11-12 20:01:02,925][4080366] Num frames 7500...
|
| 789 |
+
[2024-11-12 20:01:02,968][4080366] Num frames 7600...
|
| 790 |
+
[2024-11-12 20:01:03,015][4080366] Num frames 7700...
|
| 791 |
+
[2024-11-12 20:01:03,062][4080366] Num frames 7800...
|
| 792 |
+
[2024-11-12 20:01:03,109][4080366] Num frames 7900...
|
| 793 |
+
[2024-11-12 20:01:03,150][4080366] Num frames 8000...
|
| 794 |
+
[2024-11-12 20:01:03,194][4080366] Num frames 8100...
|
| 795 |
+
[2024-11-12 20:01:03,237][4080366] Num frames 8200...
|
| 796 |
+
[2024-11-12 20:01:03,281][4080366] Num frames 8300...
|
| 797 |
+
[2024-11-12 20:01:03,325][4080366] Num frames 8400...
|
| 798 |
+
[2024-11-12 20:01:03,372][4080366] Num frames 8500...
|
| 799 |
+
[2024-11-12 20:01:03,425][4080366] Num frames 8600...
|
| 800 |
+
[2024-11-12 20:01:03,497][4080366] Avg episode rewards: #0: 24.932, true rewards: #0: 10.807
|
| 801 |
+
[2024-11-12 20:01:03,499][4080366] Avg episode reward: 24.932, avg true_objective: 10.807
|
| 802 |
+
[2024-11-12 20:01:03,543][4080366] Num frames 8700...
|
| 803 |
+
[2024-11-12 20:01:03,601][4080366] Num frames 8800...
|
| 804 |
+
[2024-11-12 20:01:03,644][4080366] Num frames 8900...
|
| 805 |
+
[2024-11-12 20:01:03,686][4080366] Num frames 9000...
|
| 806 |
+
[2024-11-12 20:01:03,732][4080366] Num frames 9100...
|
| 807 |
+
[2024-11-12 20:01:03,776][4080366] Num frames 9200...
|
| 808 |
+
[2024-11-12 20:01:03,847][4080366] Num frames 9300...
|
| 809 |
+
[2024-11-12 20:01:03,895][4080366] Num frames 9400...
|
| 810 |
+
[2024-11-12 20:01:03,943][4080366] Num frames 9500...
|
| 811 |
+
[2024-11-12 20:01:03,986][4080366] Num frames 9600...
|
| 812 |
+
[2024-11-12 20:01:04,031][4080366] Num frames 9700...
|
| 813 |
+
[2024-11-12 20:01:04,075][4080366] Num frames 9800...
|
| 814 |
+
[2024-11-12 20:01:04,148][4080366] Avg episode rewards: #0: 25.379, true rewards: #0: 10.934
|
| 815 |
+
[2024-11-12 20:01:04,151][4080366] Avg episode reward: 25.379, avg true_objective: 10.934
|
| 816 |
+
[2024-11-12 20:01:04,226][4080366] Num frames 9900...
|
| 817 |
+
[2024-11-12 20:01:04,273][4080366] Num frames 10000...
|
| 818 |
+
[2024-11-12 20:01:04,316][4080366] Num frames 10100...
|
| 819 |
+
[2024-11-12 20:01:04,358][4080366] Num frames 10200...
|
| 820 |
+
[2024-11-12 20:01:04,400][4080366] Num frames 10300...
|
| 821 |
+
[2024-11-12 20:01:04,443][4080366] Num frames 10400...
|
| 822 |
+
[2024-11-12 20:01:04,485][4080366] Num frames 10500...
|
| 823 |
+
[2024-11-12 20:01:04,529][4080366] Num frames 10600...
|
| 824 |
+
[2024-11-12 20:01:04,570][4080366] Num frames 10700...
|
| 825 |
+
[2024-11-12 20:01:04,613][4080366] Num frames 10800...
|
| 826 |
+
[2024-11-12 20:01:04,680][4080366] Avg episode rewards: #0: 24.633, true rewards: #0: 10.833
|
| 827 |
+
[2024-11-12 20:01:04,682][4080366] Avg episode reward: 24.633, avg true_objective: 10.833
|
| 828 |
+
[2024-11-12 20:01:15,228][4080366] Replay video saved to /media/kemove/17a64fef-179c-4620-a965-511df0584b38/home/yunpeng/transformers/deep-rl-class-main/notebooks/unit8/train_dir/default_experiment/replay.mp4!
|