Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- .summary/0/events.out.tfevents.1692302374.muon +3 -0
- README.md +1 -1
- checkpoint_p0/best_000002142_8773632_reward_26.292.pth +3 -0
- checkpoint_p0/checkpoint_000002142_8773632.pth +3 -0
- checkpoint_p0/checkpoint_000002443_10006528.pth +3 -0
- config.json +4 -3
- git.diff +0 -0
- replay.mp4 +2 -2
- sf_log.txt +921 -0
.gitattributes
CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
replay.mp4 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
replay.mp4 filter=lfs diff=lfs merge=lfs -text
|
37 |
+
git.diff filter=lfs diff=lfs merge=lfs -text
|
.summary/0/events.out.tfevents.1692302374.muon
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0d659ee93ea81d0677b339e82677ccc8e48d6c0ea8947cbf2d0cd75086ecf28
|
3 |
+
size 118322
|
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 |
---
|
|
|
15 |
type: doom_health_gathering_supreme
|
16 |
metrics:
|
17 |
- type: mean_reward
|
18 |
+
value: 11.85 +/- 5.93
|
19 |
name: mean_reward
|
20 |
verified: false
|
21 |
---
|
checkpoint_p0/best_000002142_8773632_reward_26.292.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9c031d9c90b75798af34dced8e78feee14edea85369e84b36b8037e04cbc16e
|
3 |
+
size 34928806
|
checkpoint_p0/checkpoint_000002142_8773632.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46e099d7a6ad0c16466314798da0ffdfa426d8dfbd36b8e0f4724210e37200f1
|
3 |
+
size 34929220
|
checkpoint_p0/checkpoint_000002443_10006528.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ad5d590a4c04824abeb57e357ef4798f0d89eade51c85bfccfe2d53a29a740c
|
3 |
+
size 34929220
|
config.json
CHANGED
@@ -65,7 +65,7 @@
|
|
65 |
"summaries_use_frameskip": true,
|
66 |
"heartbeat_interval": 20,
|
67 |
"heartbeat_reporting_interval": 600,
|
68 |
-
"train_for_env_steps":
|
69 |
"train_for_seconds": 10000000000,
|
70 |
"save_every_sec": 120,
|
71 |
"keep_checkpoints": 2,
|
@@ -102,7 +102,7 @@
|
|
102 |
"env_framestack": 1,
|
103 |
"pixel_format": "CHW",
|
104 |
"use_record_episode_statistics": false,
|
105 |
-
"with_wandb":
|
106 |
"wandb_user": null,
|
107 |
"wandb_project": "sample_factory",
|
108 |
"wandb_group": null,
|
@@ -138,5 +138,6 @@
|
|
138 |
"train_for_env_steps": 4000000
|
139 |
},
|
140 |
"git_hash": "336df5a551fea3a2cf40925bf3083db6b4518c91",
|
141 |
-
"git_repo_name": "https://github.com/huggingface/deep-rl-class"
|
|
|
142 |
}
|
|
|
65 |
"summaries_use_frameskip": true,
|
66 |
"heartbeat_interval": 20,
|
67 |
"heartbeat_reporting_interval": 600,
|
68 |
+
"train_for_env_steps": 10000000,
|
69 |
"train_for_seconds": 10000000000,
|
70 |
"save_every_sec": 120,
|
71 |
"keep_checkpoints": 2,
|
|
|
102 |
"env_framestack": 1,
|
103 |
"pixel_format": "CHW",
|
104 |
"use_record_episode_statistics": false,
|
105 |
+
"with_wandb": true,
|
106 |
"wandb_user": null,
|
107 |
"wandb_project": "sample_factory",
|
108 |
"wandb_group": null,
|
|
|
138 |
"train_for_env_steps": 4000000
|
139 |
},
|
140 |
"git_hash": "336df5a551fea3a2cf40925bf3083db6b4518c91",
|
141 |
+
"git_repo_name": "https://github.com/huggingface/deep-rl-class",
|
142 |
+
"wandb_unique_id": "default_experiment_20230817_125929_635646"
|
143 |
}
|
git.diff
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
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:cd325b3be486b1cb6eae1418969fe4bbc491b0fdd15d9b76f669502007eaa328
|
3 |
+
size 22633936
|
sf_log.txt
CHANGED
@@ -1050,3 +1050,924 @@ main_loop: 87.5323
|
|
1050 |
[2023-08-17 12:52:44,835][131794] Avg episode rewards: #0: 20.835, true rewards: #0: 9.835
|
1051 |
[2023-08-17 12:52:44,835][131794] Avg episode reward: 20.835, avg true_objective: 9.835
|
1052 |
[2023-08-17 12:52:54,306][131794] Replay video saved to /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/replay.mp4!
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1050 |
[2023-08-17 12:52:44,835][131794] Avg episode rewards: #0: 20.835, true rewards: #0: 9.835
|
1051 |
[2023-08-17 12:52:44,835][131794] Avg episode reward: 20.835, avg true_objective: 9.835
|
1052 |
[2023-08-17 12:52:54,306][131794] Replay video saved to /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/replay.mp4!
|
1053 |
+
[2023-08-17 12:54:20,339][131794] The model has been pushed to https://huggingface.co/patonw/rl_course_vizdoom_health_gathering_supreme
|
1054 |
+
[2023-08-17 12:59:09,422][131794] Environment doom_basic already registered, overwriting...
|
1055 |
+
[2023-08-17 12:59:09,423][131794] Environment doom_two_colors_easy already registered, overwriting...
|
1056 |
+
[2023-08-17 12:59:09,423][131794] Environment doom_two_colors_hard already registered, overwriting...
|
1057 |
+
[2023-08-17 12:59:09,424][131794] Environment doom_dm already registered, overwriting...
|
1058 |
+
[2023-08-17 12:59:09,424][131794] Environment doom_dwango5 already registered, overwriting...
|
1059 |
+
[2023-08-17 12:59:09,424][131794] Environment doom_my_way_home_flat_actions already registered, overwriting...
|
1060 |
+
[2023-08-17 12:59:09,425][131794] Environment doom_defend_the_center_flat_actions already registered, overwriting...
|
1061 |
+
[2023-08-17 12:59:09,425][131794] Environment doom_my_way_home already registered, overwriting...
|
1062 |
+
[2023-08-17 12:59:09,425][131794] Environment doom_deadly_corridor already registered, overwriting...
|
1063 |
+
[2023-08-17 12:59:09,425][131794] Environment doom_defend_the_center already registered, overwriting...
|
1064 |
+
[2023-08-17 12:59:09,426][131794] Environment doom_defend_the_line already registered, overwriting...
|
1065 |
+
[2023-08-17 12:59:09,426][131794] Environment doom_health_gathering already registered, overwriting...
|
1066 |
+
[2023-08-17 12:59:09,426][131794] Environment doom_health_gathering_supreme already registered, overwriting...
|
1067 |
+
[2023-08-17 12:59:09,427][131794] Environment doom_battle already registered, overwriting...
|
1068 |
+
[2023-08-17 12:59:09,427][131794] Environment doom_battle2 already registered, overwriting...
|
1069 |
+
[2023-08-17 12:59:09,427][131794] Environment doom_duel_bots already registered, overwriting...
|
1070 |
+
[2023-08-17 12:59:09,427][131794] Environment doom_deathmatch_bots already registered, overwriting...
|
1071 |
+
[2023-08-17 12:59:09,428][131794] Environment doom_duel already registered, overwriting...
|
1072 |
+
[2023-08-17 12:59:09,428][131794] Environment doom_deathmatch_full already registered, overwriting...
|
1073 |
+
[2023-08-17 12:59:09,428][131794] Environment doom_benchmark already registered, overwriting...
|
1074 |
+
[2023-08-17 12:59:09,429][131794] register_encoder_factory: <function make_vizdoom_encoder at 0x7f0223bcab90>
|
1075 |
+
[2023-08-17 12:59:29,604][131794] Environment doom_basic already registered, overwriting...
|
1076 |
+
[2023-08-17 12:59:29,605][131794] Environment doom_two_colors_easy already registered, overwriting...
|
1077 |
+
[2023-08-17 12:59:29,606][131794] Environment doom_two_colors_hard already registered, overwriting...
|
1078 |
+
[2023-08-17 12:59:29,606][131794] Environment doom_dm already registered, overwriting...
|
1079 |
+
[2023-08-17 12:59:29,606][131794] Environment doom_dwango5 already registered, overwriting...
|
1080 |
+
[2023-08-17 12:59:29,607][131794] Environment doom_my_way_home_flat_actions already registered, overwriting...
|
1081 |
+
[2023-08-17 12:59:29,607][131794] Environment doom_defend_the_center_flat_actions already registered, overwriting...
|
1082 |
+
[2023-08-17 12:59:29,607][131794] Environment doom_my_way_home already registered, overwriting...
|
1083 |
+
[2023-08-17 12:59:29,608][131794] Environment doom_deadly_corridor already registered, overwriting...
|
1084 |
+
[2023-08-17 12:59:29,608][131794] Environment doom_defend_the_center already registered, overwriting...
|
1085 |
+
[2023-08-17 12:59:29,608][131794] Environment doom_defend_the_line already registered, overwriting...
|
1086 |
+
[2023-08-17 12:59:29,609][131794] Environment doom_health_gathering already registered, overwriting...
|
1087 |
+
[2023-08-17 12:59:29,609][131794] Environment doom_health_gathering_supreme already registered, overwriting...
|
1088 |
+
[2023-08-17 12:59:29,609][131794] Environment doom_battle already registered, overwriting...
|
1089 |
+
[2023-08-17 12:59:29,610][131794] Environment doom_battle2 already registered, overwriting...
|
1090 |
+
[2023-08-17 12:59:29,610][131794] Environment doom_duel_bots already registered, overwriting...
|
1091 |
+
[2023-08-17 12:59:29,611][131794] Environment doom_deathmatch_bots already registered, overwriting...
|
1092 |
+
[2023-08-17 12:59:29,611][131794] Environment doom_duel already registered, overwriting...
|
1093 |
+
[2023-08-17 12:59:29,611][131794] Environment doom_deathmatch_full already registered, overwriting...
|
1094 |
+
[2023-08-17 12:59:29,612][131794] Environment doom_benchmark already registered, overwriting...
|
1095 |
+
[2023-08-17 12:59:29,612][131794] register_encoder_factory: <function make_vizdoom_encoder at 0x7f0223bcab90>
|
1096 |
+
[2023-08-17 12:59:29,630][131794] Loading existing experiment configuration from /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json
|
1097 |
+
[2023-08-17 12:59:29,631][131794] Overriding arg 'train_for_env_steps' with value 10000000 passed from command line
|
1098 |
+
[2023-08-17 12:59:29,631][131794] Overriding arg 'with_wandb' with value True passed from command line
|
1099 |
+
[2023-08-17 12:59:29,634][131794] Experiment dir /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment already exists!
|
1100 |
+
[2023-08-17 12:59:29,635][131794] Resuming existing experiment from /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment...
|
1101 |
+
[2023-08-17 12:59:29,635][131794] Weights and Biases integration enabled. Project: sample_factory, user: None, group: None, unique_id: default_experiment_20230817_125929_635646
|
1102 |
+
[2023-08-17 12:59:29,819][131794] Initializing WandB...
|
1103 |
+
[2023-08-17 12:59:34,788][131794] Environment var CUDA_VISIBLE_DEVICES is 0
|
1104 |
+
|
1105 |
+
[2023-08-17 12:59:35,803][131794] Starting experiment with the following configuration:
|
1106 |
+
help=False
|
1107 |
+
algo=APPO
|
1108 |
+
env=doom_health_gathering_supreme
|
1109 |
+
experiment=default_experiment
|
1110 |
+
train_dir=/home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir
|
1111 |
+
restart_behavior=resume
|
1112 |
+
device=gpu
|
1113 |
+
seed=None
|
1114 |
+
num_policies=1
|
1115 |
+
async_rl=True
|
1116 |
+
serial_mode=False
|
1117 |
+
batched_sampling=False
|
1118 |
+
num_batches_to_accumulate=2
|
1119 |
+
worker_num_splits=2
|
1120 |
+
policy_workers_per_policy=1
|
1121 |
+
max_policy_lag=1000
|
1122 |
+
num_workers=8
|
1123 |
+
num_envs_per_worker=4
|
1124 |
+
batch_size=1024
|
1125 |
+
num_batches_per_epoch=1
|
1126 |
+
num_epochs=1
|
1127 |
+
rollout=32
|
1128 |
+
recurrence=32
|
1129 |
+
shuffle_minibatches=False
|
1130 |
+
gamma=0.99
|
1131 |
+
reward_scale=1.0
|
1132 |
+
reward_clip=1000.0
|
1133 |
+
value_bootstrap=False
|
1134 |
+
normalize_returns=True
|
1135 |
+
exploration_loss_coeff=0.001
|
1136 |
+
value_loss_coeff=0.5
|
1137 |
+
kl_loss_coeff=0.0
|
1138 |
+
exploration_loss=symmetric_kl
|
1139 |
+
gae_lambda=0.95
|
1140 |
+
ppo_clip_ratio=0.1
|
1141 |
+
ppo_clip_value=0.2
|
1142 |
+
with_vtrace=False
|
1143 |
+
vtrace_rho=1.0
|
1144 |
+
vtrace_c=1.0
|
1145 |
+
optimizer=adam
|
1146 |
+
adam_eps=1e-06
|
1147 |
+
adam_beta1=0.9
|
1148 |
+
adam_beta2=0.999
|
1149 |
+
max_grad_norm=4.0
|
1150 |
+
learning_rate=0.0001
|
1151 |
+
lr_schedule=constant
|
1152 |
+
lr_schedule_kl_threshold=0.008
|
1153 |
+
lr_adaptive_min=1e-06
|
1154 |
+
lr_adaptive_max=0.01
|
1155 |
+
obs_subtract_mean=0.0
|
1156 |
+
obs_scale=255.0
|
1157 |
+
normalize_input=True
|
1158 |
+
normalize_input_keys=None
|
1159 |
+
decorrelate_experience_max_seconds=0
|
1160 |
+
decorrelate_envs_on_one_worker=True
|
1161 |
+
actor_worker_gpus=[]
|
1162 |
+
set_workers_cpu_affinity=True
|
1163 |
+
force_envs_single_thread=False
|
1164 |
+
default_niceness=0
|
1165 |
+
log_to_file=True
|
1166 |
+
experiment_summaries_interval=10
|
1167 |
+
flush_summaries_interval=30
|
1168 |
+
stats_avg=100
|
1169 |
+
summaries_use_frameskip=True
|
1170 |
+
heartbeat_interval=20
|
1171 |
+
heartbeat_reporting_interval=600
|
1172 |
+
train_for_env_steps=10000000
|
1173 |
+
train_for_seconds=10000000000
|
1174 |
+
save_every_sec=120
|
1175 |
+
keep_checkpoints=2
|
1176 |
+
load_checkpoint_kind=latest
|
1177 |
+
save_milestones_sec=-1
|
1178 |
+
save_best_every_sec=5
|
1179 |
+
save_best_metric=reward
|
1180 |
+
save_best_after=100000
|
1181 |
+
benchmark=False
|
1182 |
+
encoder_mlp_layers=[512, 512]
|
1183 |
+
encoder_conv_architecture=convnet_simple
|
1184 |
+
encoder_conv_mlp_layers=[512]
|
1185 |
+
use_rnn=True
|
1186 |
+
rnn_size=512
|
1187 |
+
rnn_type=gru
|
1188 |
+
rnn_num_layers=1
|
1189 |
+
decoder_mlp_layers=[]
|
1190 |
+
nonlinearity=elu
|
1191 |
+
policy_initialization=orthogonal
|
1192 |
+
policy_init_gain=1.0
|
1193 |
+
actor_critic_share_weights=True
|
1194 |
+
adaptive_stddev=True
|
1195 |
+
continuous_tanh_scale=0.0
|
1196 |
+
initial_stddev=1.0
|
1197 |
+
use_env_info_cache=False
|
1198 |
+
env_gpu_actions=False
|
1199 |
+
env_gpu_observations=True
|
1200 |
+
env_frameskip=4
|
1201 |
+
env_framestack=1
|
1202 |
+
pixel_format=CHW
|
1203 |
+
use_record_episode_statistics=False
|
1204 |
+
with_wandb=True
|
1205 |
+
wandb_user=None
|
1206 |
+
wandb_project=sample_factory
|
1207 |
+
wandb_group=None
|
1208 |
+
wandb_job_type=SF
|
1209 |
+
wandb_tags=[]
|
1210 |
+
with_pbt=False
|
1211 |
+
pbt_mix_policies_in_one_env=True
|
1212 |
+
pbt_period_env_steps=5000000
|
1213 |
+
pbt_start_mutation=20000000
|
1214 |
+
pbt_replace_fraction=0.3
|
1215 |
+
pbt_mutation_rate=0.15
|
1216 |
+
pbt_replace_reward_gap=0.1
|
1217 |
+
pbt_replace_reward_gap_absolute=1e-06
|
1218 |
+
pbt_optimize_gamma=False
|
1219 |
+
pbt_target_objective=true_objective
|
1220 |
+
pbt_perturb_min=1.1
|
1221 |
+
pbt_perturb_max=1.5
|
1222 |
+
num_agents=-1
|
1223 |
+
num_humans=0
|
1224 |
+
num_bots=-1
|
1225 |
+
start_bot_difficulty=None
|
1226 |
+
timelimit=None
|
1227 |
+
res_w=128
|
1228 |
+
res_h=72
|
1229 |
+
wide_aspect_ratio=False
|
1230 |
+
eval_env_frameskip=1
|
1231 |
+
fps=35
|
1232 |
+
command_line=--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000
|
1233 |
+
cli_args={'env': 'doom_health_gathering_supreme', 'num_workers': 8, 'num_envs_per_worker': 4, 'train_for_env_steps': 4000000}
|
1234 |
+
git_hash=336df5a551fea3a2cf40925bf3083db6b4518c91
|
1235 |
+
git_repo_name=https://github.com/huggingface/deep-rl-class
|
1236 |
+
wandb_unique_id=default_experiment_20230817_125929_635646
|
1237 |
+
[2023-08-17 12:59:35,804][131794] Saving configuration to /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json...
|
1238 |
+
[2023-08-17 12:59:35,879][131794] Rollout worker 0 uses device cpu
|
1239 |
+
[2023-08-17 12:59:35,879][131794] Rollout worker 1 uses device cpu
|
1240 |
+
[2023-08-17 12:59:35,880][131794] Rollout worker 2 uses device cpu
|
1241 |
+
[2023-08-17 12:59:35,881][131794] Rollout worker 3 uses device cpu
|
1242 |
+
[2023-08-17 12:59:35,881][131794] Rollout worker 4 uses device cpu
|
1243 |
+
[2023-08-17 12:59:35,882][131794] Rollout worker 5 uses device cpu
|
1244 |
+
[2023-08-17 12:59:35,882][131794] Rollout worker 6 uses device cpu
|
1245 |
+
[2023-08-17 12:59:35,883][131794] Rollout worker 7 uses device cpu
|
1246 |
+
[2023-08-17 12:59:35,911][131794] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
1247 |
+
[2023-08-17 12:59:35,912][131794] InferenceWorker_p0-w0: min num requests: 2
|
1248 |
+
[2023-08-17 12:59:35,935][131794] Starting all processes...
|
1249 |
+
[2023-08-17 12:59:35,936][131794] Starting process learner_proc0
|
1250 |
+
[2023-08-17 12:59:35,984][131794] Starting all processes...
|
1251 |
+
[2023-08-17 12:59:35,986][131794] Starting process inference_proc0-0
|
1252 |
+
[2023-08-17 12:59:35,986][131794] Starting process rollout_proc0
|
1253 |
+
[2023-08-17 12:59:35,986][131794] Starting process rollout_proc1
|
1254 |
+
[2023-08-17 12:59:35,986][131794] Starting process rollout_proc2
|
1255 |
+
[2023-08-17 12:59:35,987][131794] Starting process rollout_proc3
|
1256 |
+
[2023-08-17 12:59:35,987][131794] Starting process rollout_proc4
|
1257 |
+
[2023-08-17 12:59:35,988][131794] Starting process rollout_proc5
|
1258 |
+
[2023-08-17 12:59:35,988][131794] Starting process rollout_proc6
|
1259 |
+
[2023-08-17 12:59:35,989][131794] Starting process rollout_proc7
|
1260 |
+
[2023-08-17 12:59:36,953][138062] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
1261 |
+
[2023-08-17 12:59:36,953][138062] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
|
1262 |
+
[2023-08-17 12:59:36,957][138062] Num visible devices: 1
|
1263 |
+
[2023-08-17 12:59:36,973][138062] Starting seed is not provided
|
1264 |
+
[2023-08-17 12:59:36,974][138062] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
1265 |
+
[2023-08-17 12:59:36,974][138062] Initializing actor-critic model on device cuda:0
|
1266 |
+
[2023-08-17 12:59:36,974][138062] RunningMeanStd input shape: (3, 72, 128)
|
1267 |
+
[2023-08-17 12:59:36,975][138062] RunningMeanStd input shape: (1,)
|
1268 |
+
[2023-08-17 12:59:36,983][138062] ConvEncoder: input_channels=3
|
1269 |
+
[2023-08-17 12:59:37,000][138076] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
1270 |
+
[2023-08-17 12:59:37,000][138076] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
|
1271 |
+
[2023-08-17 12:59:37,004][138076] Num visible devices: 1
|
1272 |
+
[2023-08-17 12:59:37,043][138062] Conv encoder output size: 512
|
1273 |
+
[2023-08-17 12:59:37,043][138062] Policy head output size: 512
|
1274 |
+
[2023-08-17 12:59:37,048][138077] Worker 1 uses CPU cores [3, 4, 5]
|
1275 |
+
[2023-08-17 12:59:37,050][138062] Created Actor Critic model with architecture:
|
1276 |
+
[2023-08-17 12:59:37,051][138062] ActorCriticSharedWeights(
|
1277 |
+
(obs_normalizer): ObservationNormalizer(
|
1278 |
+
(running_mean_std): RunningMeanStdDictInPlace(
|
1279 |
+
(running_mean_std): ModuleDict(
|
1280 |
+
(obs): RunningMeanStdInPlace()
|
1281 |
+
)
|
1282 |
+
)
|
1283 |
+
)
|
1284 |
+
(returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
|
1285 |
+
(encoder): VizdoomEncoder(
|
1286 |
+
(basic_encoder): ConvEncoder(
|
1287 |
+
(enc): RecursiveScriptModule(
|
1288 |
+
original_name=ConvEncoderImpl
|
1289 |
+
(conv_head): RecursiveScriptModule(
|
1290 |
+
original_name=Sequential
|
1291 |
+
(0): RecursiveScriptModule(original_name=Conv2d)
|
1292 |
+
(1): RecursiveScriptModule(original_name=ELU)
|
1293 |
+
(2): RecursiveScriptModule(original_name=Conv2d)
|
1294 |
+
(3): RecursiveScriptModule(original_name=ELU)
|
1295 |
+
(4): RecursiveScriptModule(original_name=Conv2d)
|
1296 |
+
(5): RecursiveScriptModule(original_name=ELU)
|
1297 |
+
)
|
1298 |
+
(mlp_layers): RecursiveScriptModule(
|
1299 |
+
original_name=Sequential
|
1300 |
+
(0): RecursiveScriptModule(original_name=Linear)
|
1301 |
+
(1): RecursiveScriptModule(original_name=ELU)
|
1302 |
+
)
|
1303 |
+
)
|
1304 |
+
)
|
1305 |
+
)
|
1306 |
+
(core): ModelCoreRNN(
|
1307 |
+
(core): GRU(512, 512)
|
1308 |
+
)
|
1309 |
+
(decoder): MlpDecoder(
|
1310 |
+
(mlp): Identity()
|
1311 |
+
)
|
1312 |
+
(critic_linear): Linear(in_features=512, out_features=1, bias=True)
|
1313 |
+
(action_parameterization): ActionParameterizationDefault(
|
1314 |
+
(distribution_linear): Linear(in_features=512, out_features=5, bias=True)
|
1315 |
+
)
|
1316 |
+
)
|
1317 |
+
[2023-08-17 12:59:37,051][138075] Worker 0 uses CPU cores [0, 1, 2]
|
1318 |
+
[2023-08-17 12:59:37,061][138081] Worker 5 uses CPU cores [15, 16, 17]
|
1319 |
+
[2023-08-17 12:59:37,061][138082] Worker 6 uses CPU cores [18, 19, 20]
|
1320 |
+
[2023-08-17 12:59:37,061][138083] Worker 7 uses CPU cores [21, 22, 23]
|
1321 |
+
[2023-08-17 12:59:37,065][138078] Worker 2 uses CPU cores [6, 7, 8]
|
1322 |
+
[2023-08-17 12:59:37,075][138079] Worker 3 uses CPU cores [9, 10, 11]
|
1323 |
+
[2023-08-17 12:59:37,079][138080] Worker 4 uses CPU cores [12, 13, 14]
|
1324 |
+
[2023-08-17 12:59:37,161][138062] Using optimizer <class 'torch.optim.adam.Adam'>
|
1325 |
+
[2023-08-17 12:59:37,161][138062] Loading state from checkpoint /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
|
1326 |
+
[2023-08-17 12:59:37,184][138062] Loading model from checkpoint
|
1327 |
+
[2023-08-17 12:59:37,187][138062] Loaded experiment state at self.train_step=978, self.env_steps=4005888
|
1328 |
+
[2023-08-17 12:59:37,187][138062] Initialized policy 0 weights for model version 978
|
1329 |
+
[2023-08-17 12:59:37,188][138062] LearnerWorker_p0 finished initialization!
|
1330 |
+
[2023-08-17 12:59:37,188][138062] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
1331 |
+
[2023-08-17 12:59:37,231][138076] RunningMeanStd input shape: (3, 72, 128)
|
1332 |
+
[2023-08-17 12:59:37,232][138076] RunningMeanStd input shape: (1,)
|
1333 |
+
[2023-08-17 12:59:37,238][138076] ConvEncoder: input_channels=3
|
1334 |
+
[2023-08-17 12:59:37,290][138076] Conv encoder output size: 512
|
1335 |
+
[2023-08-17 12:59:37,290][138076] Policy head output size: 512
|
1336 |
+
[2023-08-17 12:59:37,315][131794] Inference worker 0-0 is ready!
|
1337 |
+
[2023-08-17 12:59:37,316][131794] All inference workers are ready! Signal rollout workers to start!
|
1338 |
+
[2023-08-17 12:59:37,333][138083] Doom resolution: 160x120, resize resolution: (128, 72)
|
1339 |
+
[2023-08-17 12:59:37,334][138079] Doom resolution: 160x120, resize resolution: (128, 72)
|
1340 |
+
[2023-08-17 12:59:37,334][138080] Doom resolution: 160x120, resize resolution: (128, 72)
|
1341 |
+
[2023-08-17 12:59:37,334][138075] Doom resolution: 160x120, resize resolution: (128, 72)
|
1342 |
+
[2023-08-17 12:59:37,335][138077] Doom resolution: 160x120, resize resolution: (128, 72)
|
1343 |
+
[2023-08-17 12:59:37,335][138081] Doom resolution: 160x120, resize resolution: (128, 72)
|
1344 |
+
[2023-08-17 12:59:37,335][138078] Doom resolution: 160x120, resize resolution: (128, 72)
|
1345 |
+
[2023-08-17 12:59:37,336][138082] Doom resolution: 160x120, resize resolution: (128, 72)
|
1346 |
+
[2023-08-17 12:59:37,546][138075] Decorrelating experience for 0 frames...
|
1347 |
+
[2023-08-17 12:59:37,547][138083] Decorrelating experience for 0 frames...
|
1348 |
+
[2023-08-17 12:59:37,557][138077] Decorrelating experience for 0 frames...
|
1349 |
+
[2023-08-17 12:59:37,734][138083] Decorrelating experience for 32 frames...
|
1350 |
+
[2023-08-17 12:59:37,734][138079] Decorrelating experience for 0 frames...
|
1351 |
+
[2023-08-17 12:59:37,734][138078] Decorrelating experience for 0 frames...
|
1352 |
+
[2023-08-17 12:59:37,740][138077] Decorrelating experience for 32 frames...
|
1353 |
+
[2023-08-17 12:59:37,785][138075] Decorrelating experience for 32 frames...
|
1354 |
+
[2023-08-17 12:59:37,920][138078] Decorrelating experience for 32 frames...
|
1355 |
+
[2023-08-17 12:59:37,941][138083] Decorrelating experience for 64 frames...
|
1356 |
+
[2023-08-17 12:59:37,941][138080] Decorrelating experience for 0 frames...
|
1357 |
+
[2023-08-17 12:59:37,951][138077] Decorrelating experience for 64 frames...
|
1358 |
+
[2023-08-17 12:59:37,959][138079] Decorrelating experience for 32 frames...
|
1359 |
+
[2023-08-17 12:59:38,127][138078] Decorrelating experience for 64 frames...
|
1360 |
+
[2023-08-17 12:59:38,138][138080] Decorrelating experience for 32 frames...
|
1361 |
+
[2023-08-17 12:59:38,145][138075] Decorrelating experience for 64 frames...
|
1362 |
+
[2023-08-17 12:59:38,164][138083] Decorrelating experience for 96 frames...
|
1363 |
+
[2023-08-17 12:59:38,164][138077] Decorrelating experience for 96 frames...
|
1364 |
+
[2023-08-17 12:59:38,172][138079] Decorrelating experience for 64 frames...
|
1365 |
+
[2023-08-17 12:59:38,335][138078] Decorrelating experience for 96 frames...
|
1366 |
+
[2023-08-17 12:59:38,375][138081] Decorrelating experience for 0 frames...
|
1367 |
+
[2023-08-17 12:59:38,386][138075] Decorrelating experience for 96 frames...
|
1368 |
+
[2023-08-17 12:59:38,408][138079] Decorrelating experience for 96 frames...
|
1369 |
+
[2023-08-17 12:59:38,420][138080] Decorrelating experience for 64 frames...
|
1370 |
+
[2023-08-17 12:59:38,628][138082] Decorrelating experience for 0 frames...
|
1371 |
+
[2023-08-17 12:59:38,630][138081] Decorrelating experience for 32 frames...
|
1372 |
+
[2023-08-17 12:59:38,750][138062] Signal inference workers to stop experience collection...
|
1373 |
+
[2023-08-17 12:59:38,756][138076] InferenceWorker_p0-w0: stopping experience collection
|
1374 |
+
[2023-08-17 12:59:38,821][138082] Decorrelating experience for 32 frames...
|
1375 |
+
[2023-08-17 12:59:38,835][138081] Decorrelating experience for 64 frames...
|
1376 |
+
[2023-08-17 12:59:38,836][138080] Decorrelating experience for 96 frames...
|
1377 |
+
[2023-08-17 12:59:39,025][138082] Decorrelating experience for 64 frames...
|
1378 |
+
[2023-08-17 12:59:39,042][138081] Decorrelating experience for 96 frames...
|
1379 |
+
[2023-08-17 12:59:39,218][138082] Decorrelating experience for 96 frames...
|
1380 |
+
[2023-08-17 12:59:39,282][138062] Signal inference workers to resume experience collection...
|
1381 |
+
[2023-08-17 12:59:39,283][138076] InferenceWorker_p0-w0: resuming experience collection
|
1382 |
+
[2023-08-17 12:59:39,788][131794] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 4014080. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
|
1383 |
+
[2023-08-17 12:59:39,789][131794] Avg episode reward: [(0, '6.493')]
|
1384 |
+
[2023-08-17 12:59:40,549][138076] Updated weights for policy 0, policy_version 988 (0.0184)
|
1385 |
+
[2023-08-17 12:59:41,527][138076] Updated weights for policy 0, policy_version 998 (0.0006)
|
1386 |
+
[2023-08-17 12:59:42,585][138076] Updated weights for policy 0, policy_version 1008 (0.0006)
|
1387 |
+
[2023-08-17 12:59:43,648][138076] Updated weights for policy 0, policy_version 1018 (0.0007)
|
1388 |
+
[2023-08-17 12:59:44,652][138076] Updated weights for policy 0, policy_version 1028 (0.0006)
|
1389 |
+
[2023-08-17 12:59:44,788][131794] Fps is (10 sec: 40141.5, 60 sec: 40141.5, 300 sec: 40141.5). Total num frames: 4214784. Throughput: 0: 7708.9. Samples: 38544. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
1390 |
+
[2023-08-17 12:59:44,789][131794] Avg episode reward: [(0, '20.021')]
|
1391 |
+
[2023-08-17 12:59:45,583][138076] Updated weights for policy 0, policy_version 1038 (0.0006)
|
1392 |
+
[2023-08-17 12:59:46,560][138076] Updated weights for policy 0, policy_version 1048 (0.0006)
|
1393 |
+
[2023-08-17 12:59:47,593][138076] Updated weights for policy 0, policy_version 1058 (0.0006)
|
1394 |
+
[2023-08-17 12:59:48,603][138076] Updated weights for policy 0, policy_version 1068 (0.0006)
|
1395 |
+
[2023-08-17 12:59:49,605][138076] Updated weights for policy 0, policy_version 1078 (0.0006)
|
1396 |
+
[2023-08-17 12:59:49,788][131794] Fps is (10 sec: 40550.4, 60 sec: 40550.4, 300 sec: 40550.4). Total num frames: 4419584. Throughput: 0: 10010.8. Samples: 100108. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
|
1397 |
+
[2023-08-17 12:59:49,789][131794] Avg episode reward: [(0, '21.241')]
|
1398 |
+
[2023-08-17 12:59:50,586][138076] Updated weights for policy 0, policy_version 1088 (0.0006)
|
1399 |
+
[2023-08-17 12:59:51,564][138076] Updated weights for policy 0, policy_version 1098 (0.0006)
|
1400 |
+
[2023-08-17 12:59:52,582][138076] Updated weights for policy 0, policy_version 1108 (0.0006)
|
1401 |
+
[2023-08-17 12:59:53,540][138076] Updated weights for policy 0, policy_version 1118 (0.0006)
|
1402 |
+
[2023-08-17 12:59:54,551][138076] Updated weights for policy 0, policy_version 1128 (0.0006)
|
1403 |
+
[2023-08-17 12:59:54,788][131794] Fps is (10 sec: 41369.6, 60 sec: 40960.3, 300 sec: 40960.3). Total num frames: 4628480. Throughput: 0: 8754.6. Samples: 131318. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0)
|
1404 |
+
[2023-08-17 12:59:54,789][131794] Avg episode reward: [(0, '19.294')]
|
1405 |
+
[2023-08-17 12:59:55,528][138076] Updated weights for policy 0, policy_version 1138 (0.0006)
|
1406 |
+
[2023-08-17 12:59:55,905][131794] Heartbeat connected on Batcher_0
|
1407 |
+
[2023-08-17 12:59:55,915][131794] Heartbeat connected on LearnerWorker_p0
|
1408 |
+
[2023-08-17 12:59:55,916][131794] Heartbeat connected on InferenceWorker_p0-w0
|
1409 |
+
[2023-08-17 12:59:55,917][131794] Heartbeat connected on RolloutWorker_w0
|
1410 |
+
[2023-08-17 12:59:55,919][131794] Heartbeat connected on RolloutWorker_w1
|
1411 |
+
[2023-08-17 12:59:55,922][131794] Heartbeat connected on RolloutWorker_w2
|
1412 |
+
[2023-08-17 12:59:55,925][131794] Heartbeat connected on RolloutWorker_w3
|
1413 |
+
[2023-08-17 12:59:55,928][131794] Heartbeat connected on RolloutWorker_w4
|
1414 |
+
[2023-08-17 12:59:55,929][131794] Heartbeat connected on RolloutWorker_w5
|
1415 |
+
[2023-08-17 12:59:55,932][131794] Heartbeat connected on RolloutWorker_w6
|
1416 |
+
[2023-08-17 12:59:55,934][131794] Heartbeat connected on RolloutWorker_w7
|
1417 |
+
[2023-08-17 12:59:56,515][138076] Updated weights for policy 0, policy_version 1148 (0.0006)
|
1418 |
+
[2023-08-17 12:59:57,482][138076] Updated weights for policy 0, policy_version 1158 (0.0006)
|
1419 |
+
[2023-08-17 12:59:58,514][138076] Updated weights for policy 0, policy_version 1168 (0.0006)
|
1420 |
+
[2023-08-17 12:59:59,555][138076] Updated weights for policy 0, policy_version 1178 (0.0006)
|
1421 |
+
[2023-08-17 12:59:59,788][131794] Fps is (10 sec: 41369.8, 60 sec: 40960.1, 300 sec: 40960.1). Total num frames: 4833280. Throughput: 0: 9661.5. Samples: 193230. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
1422 |
+
[2023-08-17 12:59:59,789][131794] Avg episode reward: [(0, '25.107')]
|
1423 |
+
[2023-08-17 12:59:59,790][138062] Saving new best policy, reward=25.107!
|
1424 |
+
[2023-08-17 13:00:00,580][138076] Updated weights for policy 0, policy_version 1188 (0.0006)
|
1425 |
+
[2023-08-17 13:00:01,571][138076] Updated weights for policy 0, policy_version 1198 (0.0006)
|
1426 |
+
[2023-08-17 13:00:02,515][138076] Updated weights for policy 0, policy_version 1208 (0.0006)
|
1427 |
+
[2023-08-17 13:00:03,491][138076] Updated weights for policy 0, policy_version 1218 (0.0006)
|
1428 |
+
[2023-08-17 13:00:04,455][138076] Updated weights for policy 0, policy_version 1228 (0.0006)
|
1429 |
+
[2023-08-17 13:00:04,788][131794] Fps is (10 sec: 41369.4, 60 sec: 41123.9, 300 sec: 41123.9). Total num frames: 5042176. Throughput: 0: 10216.7. Samples: 255418. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
1430 |
+
[2023-08-17 13:00:04,789][131794] Avg episode reward: [(0, '23.711')]
|
1431 |
+
[2023-08-17 13:00:05,441][138076] Updated weights for policy 0, policy_version 1238 (0.0006)
|
1432 |
+
[2023-08-17 13:00:06,429][138076] Updated weights for policy 0, policy_version 1248 (0.0006)
|
1433 |
+
[2023-08-17 13:00:07,404][138076] Updated weights for policy 0, policy_version 1258 (0.0006)
|
1434 |
+
[2023-08-17 13:00:08,373][138076] Updated weights for policy 0, policy_version 1268 (0.0006)
|
1435 |
+
[2023-08-17 13:00:09,421][138076] Updated weights for policy 0, policy_version 1278 (0.0006)
|
1436 |
+
[2023-08-17 13:00:09,788][131794] Fps is (10 sec: 41369.8, 60 sec: 41096.7, 300 sec: 41096.7). Total num frames: 5246976. Throughput: 0: 9549.6. Samples: 286486. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
1437 |
+
[2023-08-17 13:00:09,789][131794] Avg episode reward: [(0, '20.401')]
|
1438 |
+
[2023-08-17 13:00:10,433][138076] Updated weights for policy 0, policy_version 1288 (0.0007)
|
1439 |
+
[2023-08-17 13:00:11,471][138076] Updated weights for policy 0, policy_version 1298 (0.0007)
|
1440 |
+
[2023-08-17 13:00:12,500][138076] Updated weights for policy 0, policy_version 1308 (0.0006)
|
1441 |
+
[2023-08-17 13:00:13,520][138076] Updated weights for policy 0, policy_version 1318 (0.0006)
|
1442 |
+
[2023-08-17 13:00:14,499][138076] Updated weights for policy 0, policy_version 1328 (0.0006)
|
1443 |
+
[2023-08-17 13:00:14,788][131794] Fps is (10 sec: 40550.6, 60 sec: 40960.1, 300 sec: 40960.1). Total num frames: 5447680. Throughput: 0: 9908.0. Samples: 346780. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
1444 |
+
[2023-08-17 13:00:14,789][131794] Avg episode reward: [(0, '21.480')]
|
1445 |
+
[2023-08-17 13:00:15,502][138076] Updated weights for policy 0, policy_version 1338 (0.0006)
|
1446 |
+
[2023-08-17 13:00:16,525][138076] Updated weights for policy 0, policy_version 1348 (0.0007)
|
1447 |
+
[2023-08-17 13:00:17,539][138076] Updated weights for policy 0, policy_version 1358 (0.0006)
|
1448 |
+
[2023-08-17 13:00:18,483][138076] Updated weights for policy 0, policy_version 1368 (0.0006)
|
1449 |
+
[2023-08-17 13:00:19,457][138076] Updated weights for policy 0, policy_version 1378 (0.0006)
|
1450 |
+
[2023-08-17 13:00:19,788][131794] Fps is (10 sec: 40959.7, 60 sec: 41062.4, 300 sec: 41062.4). Total num frames: 5656576. Throughput: 0: 10223.4. Samples: 408936. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
1451 |
+
[2023-08-17 13:00:19,789][131794] Avg episode reward: [(0, '24.208')]
|
1452 |
+
[2023-08-17 13:00:20,437][138076] Updated weights for policy 0, policy_version 1388 (0.0006)
|
1453 |
+
[2023-08-17 13:00:21,479][138076] Updated weights for policy 0, policy_version 1398 (0.0007)
|
1454 |
+
[2023-08-17 13:00:22,461][138076] Updated weights for policy 0, policy_version 1408 (0.0007)
|
1455 |
+
[2023-08-17 13:00:23,400][138076] Updated weights for policy 0, policy_version 1418 (0.0006)
|
1456 |
+
[2023-08-17 13:00:24,390][138076] Updated weights for policy 0, policy_version 1428 (0.0006)
|
1457 |
+
[2023-08-17 13:00:24,788][131794] Fps is (10 sec: 41779.0, 60 sec: 41142.1, 300 sec: 41142.1). Total num frames: 5865472. Throughput: 0: 9769.6. Samples: 439632. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
1458 |
+
[2023-08-17 13:00:24,789][131794] Avg episode reward: [(0, '23.461')]
|
1459 |
+
[2023-08-17 13:00:25,374][138076] Updated weights for policy 0, policy_version 1438 (0.0006)
|
1460 |
+
[2023-08-17 13:00:26,415][138076] Updated weights for policy 0, policy_version 1448 (0.0007)
|
1461 |
+
[2023-08-17 13:00:27,435][138076] Updated weights for policy 0, policy_version 1458 (0.0006)
|
1462 |
+
[2023-08-17 13:00:28,377][138076] Updated weights for policy 0, policy_version 1468 (0.0006)
|
1463 |
+
[2023-08-17 13:00:29,386][138076] Updated weights for policy 0, policy_version 1478 (0.0007)
|
1464 |
+
[2023-08-17 13:00:29,788][131794] Fps is (10 sec: 41369.8, 60 sec: 41123.9, 300 sec: 41123.9). Total num frames: 6070272. Throughput: 0: 10296.5. Samples: 501888. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
1465 |
+
[2023-08-17 13:00:29,789][131794] Avg episode reward: [(0, '23.247')]
|
1466 |
+
[2023-08-17 13:00:30,352][138076] Updated weights for policy 0, policy_version 1488 (0.0006)
|
1467 |
+
[2023-08-17 13:00:31,330][138076] Updated weights for policy 0, policy_version 1498 (0.0006)
|
1468 |
+
[2023-08-17 13:00:32,335][138076] Updated weights for policy 0, policy_version 1508 (0.0006)
|
1469 |
+
[2023-08-17 13:00:33,303][138076] Updated weights for policy 0, policy_version 1518 (0.0006)
|
1470 |
+
[2023-08-17 13:00:34,304][138076] Updated weights for policy 0, policy_version 1528 (0.0006)
|
1471 |
+
[2023-08-17 13:00:34,788][131794] Fps is (10 sec: 41369.8, 60 sec: 41183.5, 300 sec: 41183.5). Total num frames: 6279168. Throughput: 0: 10313.4. Samples: 564208. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
1472 |
+
[2023-08-17 13:00:34,789][131794] Avg episode reward: [(0, '21.354')]
|
1473 |
+
[2023-08-17 13:00:35,279][138076] Updated weights for policy 0, policy_version 1538 (0.0006)
|
1474 |
+
[2023-08-17 13:00:36,307][138076] Updated weights for policy 0, policy_version 1548 (0.0007)
|
1475 |
+
[2023-08-17 13:00:37,355][138076] Updated weights for policy 0, policy_version 1558 (0.0007)
|
1476 |
+
[2023-08-17 13:00:38,294][138076] Updated weights for policy 0, policy_version 1568 (0.0007)
|
1477 |
+
[2023-08-17 13:00:39,268][138076] Updated weights for policy 0, policy_version 1578 (0.0006)
|
1478 |
+
[2023-08-17 13:00:39,788][131794] Fps is (10 sec: 41369.6, 60 sec: 41164.9, 300 sec: 41164.9). Total num frames: 6483968. Throughput: 0: 10290.4. Samples: 594388. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
|
1479 |
+
[2023-08-17 13:00:39,789][131794] Avg episode reward: [(0, '20.492')]
|
1480 |
+
[2023-08-17 13:00:40,270][138076] Updated weights for policy 0, policy_version 1588 (0.0007)
|
1481 |
+
[2023-08-17 13:00:41,245][138076] Updated weights for policy 0, policy_version 1598 (0.0006)
|
1482 |
+
[2023-08-17 13:00:42,195][138076] Updated weights for policy 0, policy_version 1608 (0.0006)
|
1483 |
+
[2023-08-17 13:00:43,197][138076] Updated weights for policy 0, policy_version 1618 (0.0006)
|
1484 |
+
[2023-08-17 13:00:44,192][138076] Updated weights for policy 0, policy_version 1628 (0.0007)
|
1485 |
+
[2023-08-17 13:00:44,788][131794] Fps is (10 sec: 41369.3, 60 sec: 41301.3, 300 sec: 41212.1). Total num frames: 6692864. Throughput: 0: 10311.1. Samples: 657232. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
1486 |
+
[2023-08-17 13:00:44,789][131794] Avg episode reward: [(0, '22.781')]
|
1487 |
+
[2023-08-17 13:00:45,189][138076] Updated weights for policy 0, policy_version 1638 (0.0006)
|
1488 |
+
[2023-08-17 13:00:46,149][138076] Updated weights for policy 0, policy_version 1648 (0.0006)
|
1489 |
+
[2023-08-17 13:00:47,125][138076] Updated weights for policy 0, policy_version 1658 (0.0006)
|
1490 |
+
[2023-08-17 13:00:48,117][138076] Updated weights for policy 0, policy_version 1668 (0.0006)
|
1491 |
+
[2023-08-17 13:00:49,070][138076] Updated weights for policy 0, policy_version 1678 (0.0006)
|
1492 |
+
[2023-08-17 13:00:49,788][131794] Fps is (10 sec: 41778.5, 60 sec: 41369.5, 300 sec: 41252.5). Total num frames: 6901760. Throughput: 0: 10331.5. Samples: 720336. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
1493 |
+
[2023-08-17 13:00:49,789][131794] Avg episode reward: [(0, '23.809')]
|
1494 |
+
[2023-08-17 13:00:49,994][138076] Updated weights for policy 0, policy_version 1688 (0.0006)
|
1495 |
+
[2023-08-17 13:00:50,994][138076] Updated weights for policy 0, policy_version 1698 (0.0007)
|
1496 |
+
[2023-08-17 13:00:51,961][138076] Updated weights for policy 0, policy_version 1708 (0.0006)
|
1497 |
+
[2023-08-17 13:00:52,902][138076] Updated weights for policy 0, policy_version 1718 (0.0006)
|
1498 |
+
[2023-08-17 13:00:53,878][138076] Updated weights for policy 0, policy_version 1728 (0.0007)
|
1499 |
+
[2023-08-17 13:00:54,788][131794] Fps is (10 sec: 41779.3, 60 sec: 41369.6, 300 sec: 41287.7). Total num frames: 7110656. Throughput: 0: 10348.9. Samples: 752188. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
1500 |
+
[2023-08-17 13:00:54,789][131794] Avg episode reward: [(0, '20.533')]
|
1501 |
+
[2023-08-17 13:00:54,908][138076] Updated weights for policy 0, policy_version 1738 (0.0007)
|
1502 |
+
[2023-08-17 13:00:55,862][138076] Updated weights for policy 0, policy_version 1748 (0.0006)
|
1503 |
+
[2023-08-17 13:00:56,857][138076] Updated weights for policy 0, policy_version 1758 (0.0006)
|
1504 |
+
[2023-08-17 13:00:57,828][138076] Updated weights for policy 0, policy_version 1768 (0.0006)
|
1505 |
+
[2023-08-17 13:00:58,775][138076] Updated weights for policy 0, policy_version 1778 (0.0006)
|
1506 |
+
[2023-08-17 13:00:59,711][138076] Updated weights for policy 0, policy_version 1788 (0.0006)
|
1507 |
+
[2023-08-17 13:00:59,788][131794] Fps is (10 sec: 42189.4, 60 sec: 41506.1, 300 sec: 41369.6). Total num frames: 7323648. Throughput: 0: 10401.9. Samples: 814868. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
1508 |
+
[2023-08-17 13:00:59,789][131794] Avg episode reward: [(0, '24.820')]
|
1509 |
+
[2023-08-17 13:01:00,668][138076] Updated weights for policy 0, policy_version 1798 (0.0007)
|
1510 |
+
[2023-08-17 13:01:01,641][138076] Updated weights for policy 0, policy_version 1808 (0.0006)
|
1511 |
+
[2023-08-17 13:01:02,611][138076] Updated weights for policy 0, policy_version 1818 (0.0006)
|
1512 |
+
[2023-08-17 13:01:03,492][138076] Updated weights for policy 0, policy_version 1828 (0.0005)
|
1513 |
+
[2023-08-17 13:01:04,409][138076] Updated weights for policy 0, policy_version 1838 (0.0006)
|
1514 |
+
[2023-08-17 13:01:04,788][131794] Fps is (10 sec: 43417.8, 60 sec: 41711.0, 300 sec: 41538.3). Total num frames: 7544832. Throughput: 0: 10472.4. Samples: 880194. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
1515 |
+
[2023-08-17 13:01:04,789][131794] Avg episode reward: [(0, '21.285')]
|
1516 |
+
[2023-08-17 13:01:05,381][138076] Updated weights for policy 0, policy_version 1848 (0.0006)
|
1517 |
+
[2023-08-17 13:01:06,393][138076] Updated weights for policy 0, policy_version 1858 (0.0006)
|
1518 |
+
[2023-08-17 13:01:07,365][138076] Updated weights for policy 0, policy_version 1868 (0.0006)
|
1519 |
+
[2023-08-17 13:01:08,372][138076] Updated weights for policy 0, policy_version 1878 (0.0006)
|
1520 |
+
[2023-08-17 13:01:09,387][138076] Updated weights for policy 0, policy_version 1888 (0.0006)
|
1521 |
+
[2023-08-17 13:01:09,788][131794] Fps is (10 sec: 42188.8, 60 sec: 41642.6, 300 sec: 41460.6). Total num frames: 7745536. Throughput: 0: 10490.1. Samples: 911686. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
1522 |
+
[2023-08-17 13:01:09,789][131794] Avg episode reward: [(0, '23.546')]
|
1523 |
+
[2023-08-17 13:01:10,409][138076] Updated weights for policy 0, policy_version 1898 (0.0006)
|
1524 |
+
[2023-08-17 13:01:11,405][138076] Updated weights for policy 0, policy_version 1908 (0.0006)
|
1525 |
+
[2023-08-17 13:01:12,388][138076] Updated weights for policy 0, policy_version 1918 (0.0006)
|
1526 |
+
[2023-08-17 13:01:13,419][138076] Updated weights for policy 0, policy_version 1928 (0.0006)
|
1527 |
+
[2023-08-17 13:01:14,389][138076] Updated weights for policy 0, policy_version 1938 (0.0006)
|
1528 |
+
[2023-08-17 13:01:14,788][131794] Fps is (10 sec: 40959.9, 60 sec: 41779.2, 300 sec: 41477.4). Total num frames: 7954432. Throughput: 0: 10458.9. Samples: 972538. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
1529 |
+
[2023-08-17 13:01:14,789][131794] Avg episode reward: [(0, '22.888')]
|
1530 |
+
[2023-08-17 13:01:15,393][138076] Updated weights for policy 0, policy_version 1948 (0.0006)
|
1531 |
+
[2023-08-17 13:01:16,338][138076] Updated weights for policy 0, policy_version 1958 (0.0006)
|
1532 |
+
[2023-08-17 13:01:17,292][138076] Updated weights for policy 0, policy_version 1968 (0.0005)
|
1533 |
+
[2023-08-17 13:01:18,289][138076] Updated weights for policy 0, policy_version 1978 (0.0006)
|
1534 |
+
[2023-08-17 13:01:19,274][138076] Updated weights for policy 0, policy_version 1988 (0.0006)
|
1535 |
+
[2023-08-17 13:01:19,788][131794] Fps is (10 sec: 41779.1, 60 sec: 41779.2, 300 sec: 41492.5). Total num frames: 8163328. Throughput: 0: 10474.6. Samples: 1035566. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
1536 |
+
[2023-08-17 13:01:19,789][131794] Avg episode reward: [(0, '23.391')]
|
1537 |
+
[2023-08-17 13:01:20,269][138076] Updated weights for policy 0, policy_version 1998 (0.0006)
|
1538 |
+
[2023-08-17 13:01:21,317][138076] Updated weights for policy 0, policy_version 2008 (0.0007)
|
1539 |
+
[2023-08-17 13:01:22,285][138076] Updated weights for policy 0, policy_version 2018 (0.0006)
|
1540 |
+
[2023-08-17 13:01:23,339][138076] Updated weights for policy 0, policy_version 2028 (0.0007)
|
1541 |
+
[2023-08-17 13:01:24,378][138076] Updated weights for policy 0, policy_version 2038 (0.0007)
|
1542 |
+
[2023-08-17 13:01:24,788][131794] Fps is (10 sec: 40549.8, 60 sec: 41574.3, 300 sec: 41389.1). Total num frames: 8359936. Throughput: 0: 10485.4. Samples: 1066232. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
|
1543 |
+
[2023-08-17 13:01:24,789][131794] Avg episode reward: [(0, '24.663')]
|
1544 |
+
[2023-08-17 13:01:25,431][138076] Updated weights for policy 0, policy_version 2048 (0.0007)
|
1545 |
+
[2023-08-17 13:01:26,428][138076] Updated weights for policy 0, policy_version 2058 (0.0006)
|
1546 |
+
[2023-08-17 13:01:27,401][138076] Updated weights for policy 0, policy_version 2068 (0.0006)
|
1547 |
+
[2023-08-17 13:01:28,336][138076] Updated weights for policy 0, policy_version 2078 (0.0007)
|
1548 |
+
[2023-08-17 13:01:29,286][138076] Updated weights for policy 0, policy_version 2088 (0.0006)
|
1549 |
+
[2023-08-17 13:01:29,788][131794] Fps is (10 sec: 40550.2, 60 sec: 41642.6, 300 sec: 41406.8). Total num frames: 8568832. Throughput: 0: 10439.8. Samples: 1127022. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
|
1550 |
+
[2023-08-17 13:01:29,790][131794] Avg episode reward: [(0, '25.178')]
|
1551 |
+
[2023-08-17 13:01:29,791][138062] Saving new best policy, reward=25.178!
|
1552 |
+
[2023-08-17 13:01:30,320][138076] Updated weights for policy 0, policy_version 2098 (0.0007)
|
1553 |
+
[2023-08-17 13:01:31,287][138076] Updated weights for policy 0, policy_version 2108 (0.0006)
|
1554 |
+
[2023-08-17 13:01:32,279][138076] Updated weights for policy 0, policy_version 2118 (0.0006)
|
1555 |
+
[2023-08-17 13:01:33,314][138076] Updated weights for policy 0, policy_version 2128 (0.0007)
|
1556 |
+
[2023-08-17 13:01:34,294][138076] Updated weights for policy 0, policy_version 2138 (0.0006)
|
1557 |
+
[2023-08-17 13:01:34,788][131794] Fps is (10 sec: 41370.4, 60 sec: 41574.4, 300 sec: 41387.4). Total num frames: 8773632. Throughput: 0: 10409.6. Samples: 1188768. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
1558 |
+
[2023-08-17 13:01:34,789][131794] Avg episode reward: [(0, '26.292')]
|
1559 |
+
[2023-08-17 13:01:34,791][138062] Saving /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000002142_8773632.pth...
|
1560 |
+
[2023-08-17 13:01:34,827][138062] Removing /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000170_696320.pth
|
1561 |
+
[2023-08-17 13:01:34,834][138062] Saving new best policy, reward=26.292!
|
1562 |
+
[2023-08-17 13:01:35,358][138076] Updated weights for policy 0, policy_version 2148 (0.0007)
|
1563 |
+
[2023-08-17 13:01:36,310][138076] Updated weights for policy 0, policy_version 2158 (0.0006)
|
1564 |
+
[2023-08-17 13:01:37,294][138076] Updated weights for policy 0, policy_version 2168 (0.0006)
|
1565 |
+
[2023-08-17 13:01:38,264][138076] Updated weights for policy 0, policy_version 2178 (0.0006)
|
1566 |
+
[2023-08-17 13:01:39,278][138076] Updated weights for policy 0, policy_version 2188 (0.0007)
|
1567 |
+
[2023-08-17 13:01:39,788][131794] Fps is (10 sec: 41370.0, 60 sec: 41642.7, 300 sec: 41403.8). Total num frames: 8982528. Throughput: 0: 10381.0. Samples: 1219334. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
1568 |
+
[2023-08-17 13:01:39,789][131794] Avg episode reward: [(0, '21.438')]
|
1569 |
+
[2023-08-17 13:01:40,280][138076] Updated weights for policy 0, policy_version 2198 (0.0006)
|
1570 |
+
[2023-08-17 13:01:41,229][138076] Updated weights for policy 0, policy_version 2208 (0.0006)
|
1571 |
+
[2023-08-17 13:01:42,216][138076] Updated weights for policy 0, policy_version 2218 (0.0006)
|
1572 |
+
[2023-08-17 13:01:43,186][138076] Updated weights for policy 0, policy_version 2228 (0.0006)
|
1573 |
+
[2023-08-17 13:01:44,149][138076] Updated weights for policy 0, policy_version 2238 (0.0006)
|
1574 |
+
[2023-08-17 13:01:44,788][131794] Fps is (10 sec: 41779.0, 60 sec: 41642.7, 300 sec: 41418.8). Total num frames: 9191424. Throughput: 0: 10379.3. Samples: 1281936. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
1575 |
+
[2023-08-17 13:01:44,789][131794] Avg episode reward: [(0, '22.403')]
|
1576 |
+
[2023-08-17 13:01:45,098][138076] Updated weights for policy 0, policy_version 2248 (0.0006)
|
1577 |
+
[2023-08-17 13:01:46,042][138076] Updated weights for policy 0, policy_version 2258 (0.0006)
|
1578 |
+
[2023-08-17 13:01:47,015][138076] Updated weights for policy 0, policy_version 2268 (0.0006)
|
1579 |
+
[2023-08-17 13:01:47,992][138076] Updated weights for policy 0, policy_version 2278 (0.0007)
|
1580 |
+
[2023-08-17 13:01:49,037][138076] Updated weights for policy 0, policy_version 2288 (0.0007)
|
1581 |
+
[2023-08-17 13:01:49,788][131794] Fps is (10 sec: 41779.1, 60 sec: 41642.8, 300 sec: 41432.6). Total num frames: 9400320. Throughput: 0: 10329.8. Samples: 1345036. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
|
1582 |
+
[2023-08-17 13:01:49,789][131794] Avg episode reward: [(0, '24.155')]
|
1583 |
+
[2023-08-17 13:01:50,078][138076] Updated weights for policy 0, policy_version 2298 (0.0006)
|
1584 |
+
[2023-08-17 13:01:51,011][138076] Updated weights for policy 0, policy_version 2308 (0.0006)
|
1585 |
+
[2023-08-17 13:01:52,009][138076] Updated weights for policy 0, policy_version 2318 (0.0006)
|
1586 |
+
[2023-08-17 13:01:52,933][138076] Updated weights for policy 0, policy_version 2328 (0.0006)
|
1587 |
+
[2023-08-17 13:01:53,988][138076] Updated weights for policy 0, policy_version 2338 (0.0007)
|
1588 |
+
[2023-08-17 13:01:54,788][131794] Fps is (10 sec: 41779.5, 60 sec: 41642.7, 300 sec: 41445.5). Total num frames: 9609216. Throughput: 0: 10323.1. Samples: 1376224. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
|
1589 |
+
[2023-08-17 13:01:54,789][131794] Avg episode reward: [(0, '23.394')]
|
1590 |
+
[2023-08-17 13:01:54,969][138076] Updated weights for policy 0, policy_version 2348 (0.0006)
|
1591 |
+
[2023-08-17 13:01:55,990][138076] Updated weights for policy 0, policy_version 2358 (0.0006)
|
1592 |
+
[2023-08-17 13:01:56,962][138076] Updated weights for policy 0, policy_version 2368 (0.0006)
|
1593 |
+
[2023-08-17 13:01:57,986][138076] Updated weights for policy 0, policy_version 2378 (0.0006)
|
1594 |
+
[2023-08-17 13:01:58,980][138076] Updated weights for policy 0, policy_version 2388 (0.0006)
|
1595 |
+
[2023-08-17 13:01:59,788][131794] Fps is (10 sec: 41369.7, 60 sec: 41506.1, 300 sec: 41428.1). Total num frames: 9814016. Throughput: 0: 10345.8. Samples: 1438100. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
|
1596 |
+
[2023-08-17 13:01:59,789][131794] Avg episode reward: [(0, '22.972')]
|
1597 |
+
[2023-08-17 13:01:59,927][138076] Updated weights for policy 0, policy_version 2398 (0.0006)
|
1598 |
+
[2023-08-17 13:02:00,931][138076] Updated weights for policy 0, policy_version 2408 (0.0007)
|
1599 |
+
[2023-08-17 13:02:01,923][138076] Updated weights for policy 0, policy_version 2418 (0.0006)
|
1600 |
+
[2023-08-17 13:02:02,877][138076] Updated weights for policy 0, policy_version 2428 (0.0005)
|
1601 |
+
[2023-08-17 13:02:03,905][138076] Updated weights for policy 0, policy_version 2438 (0.0007)
|
1602 |
+
[2023-08-17 13:02:04,439][138062] Stopping Batcher_0...
|
1603 |
+
[2023-08-17 13:02:04,440][138062] Loop batcher_evt_loop terminating...
|
1604 |
+
[2023-08-17 13:02:04,440][138062] Saving /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000002443_10006528.pth...
|
1605 |
+
[2023-08-17 13:02:04,439][131794] Component Batcher_0 stopped!
|
1606 |
+
[2023-08-17 13:02:04,455][138076] Weights refcount: 2 0
|
1607 |
+
[2023-08-17 13:02:04,456][138076] Stopping InferenceWorker_p0-w0...
|
1608 |
+
[2023-08-17 13:02:04,456][138076] Loop inference_proc0-0_evt_loop terminating...
|
1609 |
+
[2023-08-17 13:02:04,456][131794] Component InferenceWorker_p0-w0 stopped!
|
1610 |
+
[2023-08-17 13:02:04,473][138062] Removing /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth
|
1611 |
+
[2023-08-17 13:02:04,477][138062] Saving /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000002443_10006528.pth...
|
1612 |
+
[2023-08-17 13:02:04,501][138080] Stopping RolloutWorker_w4...
|
1613 |
+
[2023-08-17 13:02:04,501][138080] Loop rollout_proc4_evt_loop terminating...
|
1614 |
+
[2023-08-17 13:02:04,501][131794] Component RolloutWorker_w4 stopped!
|
1615 |
+
[2023-08-17 13:02:04,507][138081] Stopping RolloutWorker_w5...
|
1616 |
+
[2023-08-17 13:02:04,507][138079] Stopping RolloutWorker_w3...
|
1617 |
+
[2023-08-17 13:02:04,507][138081] Loop rollout_proc5_evt_loop terminating...
|
1618 |
+
[2023-08-17 13:02:04,507][138079] Loop rollout_proc3_evt_loop terminating...
|
1619 |
+
[2023-08-17 13:02:04,507][131794] Component RolloutWorker_w3 stopped!
|
1620 |
+
[2023-08-17 13:02:04,508][131794] Component RolloutWorker_w5 stopped!
|
1621 |
+
[2023-08-17 13:02:04,511][138083] Stopping RolloutWorker_w7...
|
1622 |
+
[2023-08-17 13:02:04,511][138083] Loop rollout_proc7_evt_loop terminating...
|
1623 |
+
[2023-08-17 13:02:04,511][131794] Component RolloutWorker_w7 stopped!
|
1624 |
+
[2023-08-17 13:02:04,512][138078] Stopping RolloutWorker_w2...
|
1625 |
+
[2023-08-17 13:02:04,512][138078] Loop rollout_proc2_evt_loop terminating...
|
1626 |
+
[2023-08-17 13:02:04,513][138082] Stopping RolloutWorker_w6...
|
1627 |
+
[2023-08-17 13:02:04,512][131794] Component RolloutWorker_w2 stopped!
|
1628 |
+
[2023-08-17 13:02:04,513][138082] Loop rollout_proc6_evt_loop terminating...
|
1629 |
+
[2023-08-17 13:02:04,513][131794] Component RolloutWorker_w6 stopped!
|
1630 |
+
[2023-08-17 13:02:04,519][138077] Stopping RolloutWorker_w1...
|
1631 |
+
[2023-08-17 13:02:04,519][138077] Loop rollout_proc1_evt_loop terminating...
|
1632 |
+
[2023-08-17 13:02:04,519][131794] Component RolloutWorker_w1 stopped!
|
1633 |
+
[2023-08-17 13:02:04,535][138062] Stopping LearnerWorker_p0...
|
1634 |
+
[2023-08-17 13:02:04,536][138062] Loop learner_proc0_evt_loop terminating...
|
1635 |
+
[2023-08-17 13:02:04,535][131794] Component LearnerWorker_p0 stopped!
|
1636 |
+
[2023-08-17 13:02:04,539][138075] Stopping RolloutWorker_w0...
|
1637 |
+
[2023-08-17 13:02:04,540][138075] Loop rollout_proc0_evt_loop terminating...
|
1638 |
+
[2023-08-17 13:02:04,539][131794] Component RolloutWorker_w0 stopped!
|
1639 |
+
[2023-08-17 13:02:04,540][131794] Waiting for process learner_proc0 to stop...
|
1640 |
+
[2023-08-17 13:02:05,188][131794] Waiting for process inference_proc0-0 to join...
|
1641 |
+
[2023-08-17 13:02:05,189][131794] Waiting for process rollout_proc0 to join...
|
1642 |
+
[2023-08-17 13:02:05,190][131794] Waiting for process rollout_proc1 to join...
|
1643 |
+
[2023-08-17 13:02:05,190][131794] Waiting for process rollout_proc2 to join...
|
1644 |
+
[2023-08-17 13:02:05,191][131794] Waiting for process rollout_proc3 to join...
|
1645 |
+
[2023-08-17 13:02:05,191][131794] Waiting for process rollout_proc4 to join...
|
1646 |
+
[2023-08-17 13:02:05,192][131794] Waiting for process rollout_proc5 to join...
|
1647 |
+
[2023-08-17 13:02:05,193][131794] Waiting for process rollout_proc6 to join...
|
1648 |
+
[2023-08-17 13:02:05,193][131794] Waiting for process rollout_proc7 to join...
|
1649 |
+
[2023-08-17 13:02:05,194][131794] Batcher 0 profile tree view:
|
1650 |
+
batching: 12.6388, releasing_batches: 0.0155
|
1651 |
+
[2023-08-17 13:02:05,194][131794] InferenceWorker_p0-w0 profile tree view:
|
1652 |
+
wait_policy: 0.0000
|
1653 |
+
wait_policy_total: 2.6989
|
1654 |
+
update_model: 2.1930
|
1655 |
+
weight_update: 0.0007
|
1656 |
+
one_step: 0.0019
|
1657 |
+
handle_policy_step: 134.6435
|
1658 |
+
deserialize: 6.0242, stack: 0.6403, obs_to_device_normalize: 30.9018, forward: 66.9499, send_messages: 8.4976
|
1659 |
+
prepare_outputs: 15.8515
|
1660 |
+
to_cpu: 10.1908
|
1661 |
+
[2023-08-17 13:02:05,195][131794] Learner 0 profile tree view:
|
1662 |
+
misc: 0.0062, prepare_batch: 6.1025
|
1663 |
+
train: 17.4443
|
1664 |
+
epoch_init: 0.0048, minibatch_init: 0.0045, losses_postprocess: 0.4413, kl_divergence: 0.3416, after_optimizer: 0.4372
|
1665 |
+
calculate_losses: 6.4031
|
1666 |
+
losses_init: 0.0025, forward_head: 0.4213, bptt_initial: 3.8098, tail: 0.4256, advantages_returns: 0.1042, losses: 0.8304
|
1667 |
+
bptt: 0.6899
|
1668 |
+
bptt_forward_core: 0.6553
|
1669 |
+
update: 9.5344
|
1670 |
+
clip: 4.9986
|
1671 |
+
[2023-08-17 13:02:05,195][131794] RolloutWorker_w0 profile tree view:
|
1672 |
+
wait_for_trajectories: 0.1145, enqueue_policy_requests: 4.7133, env_step: 65.9256, overhead: 6.2646, complete_rollouts: 0.1526
|
1673 |
+
save_policy_outputs: 6.3662
|
1674 |
+
split_output_tensors: 2.9670
|
1675 |
+
[2023-08-17 13:02:05,195][131794] RolloutWorker_w7 profile tree view:
|
1676 |
+
wait_for_trajectories: 0.1125, enqueue_policy_requests: 4.8606, env_step: 68.5610, overhead: 6.5985, complete_rollouts: 0.1617
|
1677 |
+
save_policy_outputs: 6.9442
|
1678 |
+
split_output_tensors: 3.1602
|
1679 |
+
[2023-08-17 13:02:05,196][131794] Loop Runner_EvtLoop terminating...
|
1680 |
+
[2023-08-17 13:02:05,197][131794] Runner profile tree view:
|
1681 |
+
main_loop: 149.2631
|
1682 |
+
[2023-08-17 13:02:05,197][131794] Collected {0: 10006528}, FPS: 40201.8
|
1683 |
+
[2023-08-17 13:02:20,239][131794] Loading existing experiment configuration from /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json
|
1684 |
+
[2023-08-17 13:02:20,239][131794] Overriding arg 'num_workers' with value 1 passed from command line
|
1685 |
+
[2023-08-17 13:02:20,240][131794] Adding new argument 'no_render'=True that is not in the saved config file!
|
1686 |
+
[2023-08-17 13:02:20,240][131794] Adding new argument 'save_video'=True that is not in the saved config file!
|
1687 |
+
[2023-08-17 13:02:20,241][131794] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
|
1688 |
+
[2023-08-17 13:02:20,241][131794] Adding new argument 'video_name'=None that is not in the saved config file!
|
1689 |
+
[2023-08-17 13:02:20,242][131794] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
|
1690 |
+
[2023-08-17 13:02:20,243][131794] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
|
1691 |
+
[2023-08-17 13:02:20,243][131794] Adding new argument 'push_to_hub'=False that is not in the saved config file!
|
1692 |
+
[2023-08-17 13:02:20,244][131794] Adding new argument 'hf_repository'=None that is not in the saved config file!
|
1693 |
+
[2023-08-17 13:02:20,244][131794] Adding new argument 'policy_index'=0 that is not in the saved config file!
|
1694 |
+
[2023-08-17 13:02:20,245][131794] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
|
1695 |
+
[2023-08-17 13:02:20,246][131794] Adding new argument 'train_script'=None that is not in the saved config file!
|
1696 |
+
[2023-08-17 13:02:20,246][131794] Adding new argument 'enjoy_script'=None that is not in the saved config file!
|
1697 |
+
[2023-08-17 13:02:20,247][131794] Using frameskip 1 and render_action_repeat=4 for evaluation
|
1698 |
+
[2023-08-17 13:02:20,250][131794] RunningMeanStd input shape: (3, 72, 128)
|
1699 |
+
[2023-08-17 13:02:20,251][131794] RunningMeanStd input shape: (1,)
|
1700 |
+
[2023-08-17 13:02:20,257][131794] ConvEncoder: input_channels=3
|
1701 |
+
[2023-08-17 13:02:20,280][131794] Conv encoder output size: 512
|
1702 |
+
[2023-08-17 13:02:20,281][131794] Policy head output size: 512
|
1703 |
+
[2023-08-17 13:02:20,723][131794] Loading state from checkpoint /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000002443_10006528.pth...
|
1704 |
+
[2023-08-17 13:02:21,021][131794] Num frames 100...
|
1705 |
+
[2023-08-17 13:02:21,076][131794] Num frames 200...
|
1706 |
+
[2023-08-17 13:02:21,129][131794] Num frames 300...
|
1707 |
+
[2023-08-17 13:02:21,183][131794] Num frames 400...
|
1708 |
+
[2023-08-17 13:02:21,237][131794] Num frames 500...
|
1709 |
+
[2023-08-17 13:02:21,314][131794] Avg episode rewards: #0: 8.440, true rewards: #0: 5.440
|
1710 |
+
[2023-08-17 13:02:21,315][131794] Avg episode reward: 8.440, avg true_objective: 5.440
|
1711 |
+
[2023-08-17 13:02:21,348][131794] Num frames 600...
|
1712 |
+
[2023-08-17 13:02:21,402][131794] Num frames 700...
|
1713 |
+
[2023-08-17 13:02:21,457][131794] Num frames 800...
|
1714 |
+
[2023-08-17 13:02:21,512][131794] Num frames 900...
|
1715 |
+
[2023-08-17 13:02:21,567][131794] Num frames 1000...
|
1716 |
+
[2023-08-17 13:02:21,623][131794] Num frames 1100...
|
1717 |
+
[2023-08-17 13:02:21,679][131794] Num frames 1200...
|
1718 |
+
[2023-08-17 13:02:21,736][131794] Num frames 1300...
|
1719 |
+
[2023-08-17 13:02:21,793][131794] Num frames 1400...
|
1720 |
+
[2023-08-17 13:02:21,852][131794] Num frames 1500...
|
1721 |
+
[2023-08-17 13:02:21,912][131794] Num frames 1600...
|
1722 |
+
[2023-08-17 13:02:21,969][131794] Num frames 1700...
|
1723 |
+
[2023-08-17 13:02:22,026][131794] Num frames 1800...
|
1724 |
+
[2023-08-17 13:02:22,081][131794] Num frames 1900...
|
1725 |
+
[2023-08-17 13:02:22,137][131794] Num frames 2000...
|
1726 |
+
[2023-08-17 13:02:22,193][131794] Num frames 2100...
|
1727 |
+
[2023-08-17 13:02:22,251][131794] Num frames 2200...
|
1728 |
+
[2023-08-17 13:02:22,308][131794] Num frames 2300...
|
1729 |
+
[2023-08-17 13:02:22,367][131794] Num frames 2400...
|
1730 |
+
[2023-08-17 13:02:22,424][131794] Num frames 2500...
|
1731 |
+
[2023-08-17 13:02:22,482][131794] Num frames 2600...
|
1732 |
+
[2023-08-17 13:02:22,560][131794] Avg episode rewards: #0: 31.219, true rewards: #0: 13.220
|
1733 |
+
[2023-08-17 13:02:22,560][131794] Avg episode reward: 31.219, avg true_objective: 13.220
|
1734 |
+
[2023-08-17 13:02:22,593][131794] Num frames 2700...
|
1735 |
+
[2023-08-17 13:02:22,649][131794] Num frames 2800...
|
1736 |
+
[2023-08-17 13:02:22,705][131794] Num frames 2900...
|
1737 |
+
[2023-08-17 13:02:22,760][131794] Num frames 3000...
|
1738 |
+
[2023-08-17 13:02:22,817][131794] Num frames 3100...
|
1739 |
+
[2023-08-17 13:02:22,874][131794] Num frames 3200...
|
1740 |
+
[2023-08-17 13:02:22,931][131794] Num frames 3300...
|
1741 |
+
[2023-08-17 13:02:22,986][131794] Num frames 3400...
|
1742 |
+
[2023-08-17 13:02:23,040][131794] Num frames 3500...
|
1743 |
+
[2023-08-17 13:02:23,095][131794] Num frames 3600...
|
1744 |
+
[2023-08-17 13:02:23,150][131794] Num frames 3700...
|
1745 |
+
[2023-08-17 13:02:23,204][131794] Num frames 3800...
|
1746 |
+
[2023-08-17 13:02:23,310][131794] Avg episode rewards: #0: 30.323, true rewards: #0: 12.990
|
1747 |
+
[2023-08-17 13:02:23,311][131794] Avg episode reward: 30.323, avg true_objective: 12.990
|
1748 |
+
[2023-08-17 13:02:23,313][131794] Num frames 3900...
|
1749 |
+
[2023-08-17 13:02:23,369][131794] Num frames 4000...
|
1750 |
+
[2023-08-17 13:02:23,426][131794] Num frames 4100...
|
1751 |
+
[2023-08-17 13:02:23,484][131794] Num frames 4200...
|
1752 |
+
[2023-08-17 13:02:23,539][131794] Num frames 4300...
|
1753 |
+
[2023-08-17 13:02:23,595][131794] Num frames 4400...
|
1754 |
+
[2023-08-17 13:02:23,650][131794] Num frames 4500...
|
1755 |
+
[2023-08-17 13:02:23,706][131794] Num frames 4600...
|
1756 |
+
[2023-08-17 13:02:23,761][131794] Num frames 4700...
|
1757 |
+
[2023-08-17 13:02:23,816][131794] Num frames 4800...
|
1758 |
+
[2023-08-17 13:02:23,872][131794] Num frames 4900...
|
1759 |
+
[2023-08-17 13:02:23,929][131794] Num frames 5000...
|
1760 |
+
[2023-08-17 13:02:23,984][131794] Num frames 5100...
|
1761 |
+
[2023-08-17 13:02:24,039][131794] Num frames 5200...
|
1762 |
+
[2023-08-17 13:02:24,096][131794] Num frames 5300...
|
1763 |
+
[2023-08-17 13:02:24,152][131794] Num frames 5400...
|
1764 |
+
[2023-08-17 13:02:24,242][131794] Avg episode rewards: #0: 31.662, true rewards: #0: 13.662
|
1765 |
+
[2023-08-17 13:02:24,243][131794] Avg episode reward: 31.662, avg true_objective: 13.662
|
1766 |
+
[2023-08-17 13:02:24,263][131794] Num frames 5500...
|
1767 |
+
[2023-08-17 13:02:24,318][131794] Num frames 5600...
|
1768 |
+
[2023-08-17 13:02:24,374][131794] Num frames 5700...
|
1769 |
+
[2023-08-17 13:02:24,428][131794] Num frames 5800...
|
1770 |
+
[2023-08-17 13:02:24,483][131794] Num frames 5900...
|
1771 |
+
[2023-08-17 13:02:24,538][131794] Num frames 6000...
|
1772 |
+
[2023-08-17 13:02:24,631][131794] Avg episode rewards: #0: 27.146, true rewards: #0: 12.146
|
1773 |
+
[2023-08-17 13:02:24,632][131794] Avg episode reward: 27.146, avg true_objective: 12.146
|
1774 |
+
[2023-08-17 13:02:24,648][131794] Num frames 6100...
|
1775 |
+
[2023-08-17 13:02:24,706][131794] Num frames 6200...
|
1776 |
+
[2023-08-17 13:02:24,763][131794] Num frames 6300...
|
1777 |
+
[2023-08-17 13:02:24,818][131794] Num frames 6400...
|
1778 |
+
[2023-08-17 13:02:24,872][131794] Num frames 6500...
|
1779 |
+
[2023-08-17 13:02:24,937][131794] Avg episode rewards: #0: 23.535, true rewards: #0: 10.868
|
1780 |
+
[2023-08-17 13:02:24,938][131794] Avg episode reward: 23.535, avg true_objective: 10.868
|
1781 |
+
[2023-08-17 13:02:24,985][131794] Num frames 6600...
|
1782 |
+
[2023-08-17 13:02:25,040][131794] Num frames 6700...
|
1783 |
+
[2023-08-17 13:02:25,094][131794] Num frames 6800...
|
1784 |
+
[2023-08-17 13:02:25,150][131794] Num frames 6900...
|
1785 |
+
[2023-08-17 13:02:25,205][131794] Num frames 7000...
|
1786 |
+
[2023-08-17 13:02:25,260][131794] Num frames 7100...
|
1787 |
+
[2023-08-17 13:02:25,315][131794] Num frames 7200...
|
1788 |
+
[2023-08-17 13:02:25,416][131794] Avg episode rewards: #0: 21.984, true rewards: #0: 10.413
|
1789 |
+
[2023-08-17 13:02:25,417][131794] Avg episode reward: 21.984, avg true_objective: 10.413
|
1790 |
+
[2023-08-17 13:02:25,424][131794] Num frames 7300...
|
1791 |
+
[2023-08-17 13:02:25,479][131794] Num frames 7400...
|
1792 |
+
[2023-08-17 13:02:25,535][131794] Num frames 7500...
|
1793 |
+
[2023-08-17 13:02:25,591][131794] Num frames 7600...
|
1794 |
+
[2023-08-17 13:02:25,646][131794] Num frames 7700...
|
1795 |
+
[2023-08-17 13:02:25,746][131794] Avg episode rewards: #0: 20.484, true rewards: #0: 9.734
|
1796 |
+
[2023-08-17 13:02:25,747][131794] Avg episode reward: 20.484, avg true_objective: 9.734
|
1797 |
+
[2023-08-17 13:02:25,755][131794] Num frames 7800...
|
1798 |
+
[2023-08-17 13:02:25,809][131794] Num frames 7900...
|
1799 |
+
[2023-08-17 13:02:25,864][131794] Num frames 8000...
|
1800 |
+
[2023-08-17 13:02:25,918][131794] Num frames 8100...
|
1801 |
+
[2023-08-17 13:02:25,972][131794] Num frames 8200...
|
1802 |
+
[2023-08-17 13:02:26,027][131794] Num frames 8300...
|
1803 |
+
[2023-08-17 13:02:26,082][131794] Num frames 8400...
|
1804 |
+
[2023-08-17 13:02:26,167][131794] Avg episode rewards: #0: 19.510, true rewards: #0: 9.399
|
1805 |
+
[2023-08-17 13:02:26,168][131794] Avg episode reward: 19.510, avg true_objective: 9.399
|
1806 |
+
[2023-08-17 13:02:26,190][131794] Num frames 8500...
|
1807 |
+
[2023-08-17 13:02:26,245][131794] Num frames 8600...
|
1808 |
+
[2023-08-17 13:02:26,300][131794] Num frames 8700...
|
1809 |
+
[2023-08-17 13:02:26,355][131794] Num frames 8800...
|
1810 |
+
[2023-08-17 13:02:26,410][131794] Num frames 8900...
|
1811 |
+
[2023-08-17 13:02:26,466][131794] Avg episode rewards: #0: 18.107, true rewards: #0: 8.907
|
1812 |
+
[2023-08-17 13:02:26,467][131794] Avg episode reward: 18.107, avg true_objective: 8.907
|
1813 |
+
[2023-08-17 13:02:34,995][131794] Replay video saved to /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/replay.mp4!
|
1814 |
+
[2023-08-17 13:03:03,228][131794] Loading existing experiment configuration from /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json
|
1815 |
+
[2023-08-17 13:03:03,228][131794] Overriding arg 'num_workers' with value 1 passed from command line
|
1816 |
+
[2023-08-17 13:03:03,229][131794] Adding new argument 'no_render'=True that is not in the saved config file!
|
1817 |
+
[2023-08-17 13:03:03,229][131794] Adding new argument 'save_video'=True that is not in the saved config file!
|
1818 |
+
[2023-08-17 13:03:03,230][131794] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
|
1819 |
+
[2023-08-17 13:03:03,230][131794] Adding new argument 'video_name'=None that is not in the saved config file!
|
1820 |
+
[2023-08-17 13:03:03,230][131794] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
|
1821 |
+
[2023-08-17 13:03:03,231][131794] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
|
1822 |
+
[2023-08-17 13:03:03,231][131794] Adding new argument 'push_to_hub'=True that is not in the saved config file!
|
1823 |
+
[2023-08-17 13:03:03,231][131794] Adding new argument 'hf_repository'='patonw/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
|
1824 |
+
[2023-08-17 13:03:03,232][131794] Adding new argument 'policy_index'=0 that is not in the saved config file!
|
1825 |
+
[2023-08-17 13:03:03,232][131794] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
|
1826 |
+
[2023-08-17 13:03:03,233][131794] Adding new argument 'train_script'=None that is not in the saved config file!
|
1827 |
+
[2023-08-17 13:03:03,233][131794] Adding new argument 'enjoy_script'=None that is not in the saved config file!
|
1828 |
+
[2023-08-17 13:03:03,233][131794] Using frameskip 1 and render_action_repeat=4 for evaluation
|
1829 |
+
[2023-08-17 13:03:03,238][131794] RunningMeanStd input shape: (3, 72, 128)
|
1830 |
+
[2023-08-17 13:03:03,239][131794] RunningMeanStd input shape: (1,)
|
1831 |
+
[2023-08-17 13:03:03,245][131794] ConvEncoder: input_channels=3
|
1832 |
+
[2023-08-17 13:03:03,266][131794] Conv encoder output size: 512
|
1833 |
+
[2023-08-17 13:03:03,267][131794] Policy head output size: 512
|
1834 |
+
[2023-08-17 13:03:03,283][131794] Loading state from checkpoint /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000002443_10006528.pth...
|
1835 |
+
[2023-08-17 13:03:03,601][131794] Num frames 100...
|
1836 |
+
[2023-08-17 13:03:03,655][131794] Num frames 200...
|
1837 |
+
[2023-08-17 13:03:03,719][131794] Num frames 300...
|
1838 |
+
[2023-08-17 13:03:03,778][131794] Num frames 400...
|
1839 |
+
[2023-08-17 13:03:03,835][131794] Num frames 500...
|
1840 |
+
[2023-08-17 13:03:03,888][131794] Num frames 600...
|
1841 |
+
[2023-08-17 13:03:03,942][131794] Num frames 700...
|
1842 |
+
[2023-08-17 13:03:03,995][131794] Num frames 800...
|
1843 |
+
[2023-08-17 13:03:04,049][131794] Num frames 900...
|
1844 |
+
[2023-08-17 13:03:04,102][131794] Num frames 1000...
|
1845 |
+
[2023-08-17 13:03:04,156][131794] Num frames 1100...
|
1846 |
+
[2023-08-17 13:03:04,210][131794] Num frames 1200...
|
1847 |
+
[2023-08-17 13:03:04,265][131794] Num frames 1300...
|
1848 |
+
[2023-08-17 13:03:04,319][131794] Num frames 1400...
|
1849 |
+
[2023-08-17 13:03:04,376][131794] Num frames 1500...
|
1850 |
+
[2023-08-17 13:03:04,430][131794] Num frames 1600...
|
1851 |
+
[2023-08-17 13:03:04,485][131794] Num frames 1700...
|
1852 |
+
[2023-08-17 13:03:04,541][131794] Num frames 1800...
|
1853 |
+
[2023-08-17 13:03:04,597][131794] Num frames 1900...
|
1854 |
+
[2023-08-17 13:03:04,655][131794] Num frames 2000...
|
1855 |
+
[2023-08-17 13:03:04,715][131794] Num frames 2100...
|
1856 |
+
[2023-08-17 13:03:04,766][131794] Avg episode rewards: #0: 53.999, true rewards: #0: 21.000
|
1857 |
+
[2023-08-17 13:03:04,767][131794] Avg episode reward: 53.999, avg true_objective: 21.000
|
1858 |
+
[2023-08-17 13:03:04,825][131794] Num frames 2200...
|
1859 |
+
[2023-08-17 13:03:04,883][131794] Num frames 2300...
|
1860 |
+
[2023-08-17 13:03:04,942][131794] Num frames 2400...
|
1861 |
+
[2023-08-17 13:03:04,999][131794] Num frames 2500...
|
1862 |
+
[2023-08-17 13:03:05,056][131794] Num frames 2600...
|
1863 |
+
[2023-08-17 13:03:05,114][131794] Num frames 2700...
|
1864 |
+
[2023-08-17 13:03:05,173][131794] Num frames 2800...
|
1865 |
+
[2023-08-17 13:03:05,231][131794] Num frames 2900...
|
1866 |
+
[2023-08-17 13:03:05,291][131794] Num frames 3000...
|
1867 |
+
[2023-08-17 13:03:05,348][131794] Num frames 3100...
|
1868 |
+
[2023-08-17 13:03:05,408][131794] Num frames 3200...
|
1869 |
+
[2023-08-17 13:03:05,466][131794] Num frames 3300...
|
1870 |
+
[2023-08-17 13:03:05,526][131794] Num frames 3400...
|
1871 |
+
[2023-08-17 13:03:05,586][131794] Num frames 3500...
|
1872 |
+
[2023-08-17 13:03:05,672][131794] Avg episode rewards: #0: 44.770, true rewards: #0: 17.770
|
1873 |
+
[2023-08-17 13:03:05,673][131794] Avg episode reward: 44.770, avg true_objective: 17.770
|
1874 |
+
[2023-08-17 13:03:05,699][131794] Num frames 3600...
|
1875 |
+
[2023-08-17 13:03:05,759][131794] Num frames 3700...
|
1876 |
+
[2023-08-17 13:03:05,819][131794] Num frames 3800...
|
1877 |
+
[2023-08-17 13:03:05,878][131794] Num frames 3900...
|
1878 |
+
[2023-08-17 13:03:05,936][131794] Num frames 4000...
|
1879 |
+
[2023-08-17 13:03:05,993][131794] Num frames 4100...
|
1880 |
+
[2023-08-17 13:03:06,050][131794] Num frames 4200...
|
1881 |
+
[2023-08-17 13:03:06,108][131794] Num frames 4300...
|
1882 |
+
[2023-08-17 13:03:06,166][131794] Num frames 4400...
|
1883 |
+
[2023-08-17 13:03:06,225][131794] Num frames 4500...
|
1884 |
+
[2023-08-17 13:03:06,284][131794] Num frames 4600...
|
1885 |
+
[2023-08-17 13:03:06,343][131794] Num frames 4700...
|
1886 |
+
[2023-08-17 13:03:06,401][131794] Num frames 4800...
|
1887 |
+
[2023-08-17 13:03:06,463][131794] Num frames 4900...
|
1888 |
+
[2023-08-17 13:03:06,521][131794] Num frames 5000...
|
1889 |
+
[2023-08-17 13:03:06,579][131794] Num frames 5100...
|
1890 |
+
[2023-08-17 13:03:06,638][131794] Num frames 5200...
|
1891 |
+
[2023-08-17 13:03:06,696][131794] Num frames 5300...
|
1892 |
+
[2023-08-17 13:03:06,753][131794] Num frames 5400...
|
1893 |
+
[2023-08-17 13:03:06,812][131794] Num frames 5500...
|
1894 |
+
[2023-08-17 13:03:06,870][131794] Num frames 5600...
|
1895 |
+
[2023-08-17 13:03:06,954][131794] Avg episode rewards: #0: 48.179, true rewards: #0: 18.847
|
1896 |
+
[2023-08-17 13:03:06,955][131794] Avg episode reward: 48.179, avg true_objective: 18.847
|
1897 |
+
[2023-08-17 13:03:06,981][131794] Num frames 5700...
|
1898 |
+
[2023-08-17 13:03:07,037][131794] Num frames 5800...
|
1899 |
+
[2023-08-17 13:03:07,094][131794] Num frames 5900...
|
1900 |
+
[2023-08-17 13:03:07,152][131794] Num frames 6000...
|
1901 |
+
[2023-08-17 13:03:07,210][131794] Num frames 6100...
|
1902 |
+
[2023-08-17 13:03:07,269][131794] Num frames 6200...
|
1903 |
+
[2023-08-17 13:03:07,327][131794] Num frames 6300...
|
1904 |
+
[2023-08-17 13:03:07,385][131794] Num frames 6400...
|
1905 |
+
[2023-08-17 13:03:07,443][131794] Num frames 6500...
|
1906 |
+
[2023-08-17 13:03:07,500][131794] Num frames 6600...
|
1907 |
+
[2023-08-17 13:03:07,559][131794] Num frames 6700...
|
1908 |
+
[2023-08-17 13:03:07,617][131794] Num frames 6800...
|
1909 |
+
[2023-08-17 13:03:07,679][131794] Avg episode rewards: #0: 42.537, true rewards: #0: 17.038
|
1910 |
+
[2023-08-17 13:03:07,679][131794] Avg episode reward: 42.537, avg true_objective: 17.038
|
1911 |
+
[2023-08-17 13:03:07,728][131794] Num frames 6900...
|
1912 |
+
[2023-08-17 13:03:07,787][131794] Num frames 7000...
|
1913 |
+
[2023-08-17 13:03:07,845][131794] Num frames 7100...
|
1914 |
+
[2023-08-17 13:03:07,903][131794] Num frames 7200...
|
1915 |
+
[2023-08-17 13:03:07,961][131794] Num frames 7300...
|
1916 |
+
[2023-08-17 13:03:08,020][131794] Num frames 7400...
|
1917 |
+
[2023-08-17 13:03:08,078][131794] Num frames 7500...
|
1918 |
+
[2023-08-17 13:03:08,137][131794] Num frames 7600...
|
1919 |
+
[2023-08-17 13:03:08,195][131794] Num frames 7700...
|
1920 |
+
[2023-08-17 13:03:08,255][131794] Num frames 7800...
|
1921 |
+
[2023-08-17 13:03:08,313][131794] Num frames 7900...
|
1922 |
+
[2023-08-17 13:03:08,371][131794] Num frames 8000...
|
1923 |
+
[2023-08-17 13:03:08,430][131794] Num frames 8100...
|
1924 |
+
[2023-08-17 13:03:08,492][131794] Num frames 8200...
|
1925 |
+
[2023-08-17 13:03:08,551][131794] Num frames 8300...
|
1926 |
+
[2023-08-17 13:03:08,610][131794] Num frames 8400...
|
1927 |
+
[2023-08-17 13:03:08,699][131794] Avg episode rewards: #0: 41.920, true rewards: #0: 16.920
|
1928 |
+
[2023-08-17 13:03:08,699][131794] Avg episode reward: 41.920, avg true_objective: 16.920
|
1929 |
+
[2023-08-17 13:03:08,724][131794] Num frames 8500...
|
1930 |
+
[2023-08-17 13:03:08,783][131794] Num frames 8600...
|
1931 |
+
[2023-08-17 13:03:08,842][131794] Num frames 8700...
|
1932 |
+
[2023-08-17 13:03:08,901][131794] Num frames 8800...
|
1933 |
+
[2023-08-17 13:03:08,960][131794] Num frames 8900...
|
1934 |
+
[2023-08-17 13:03:09,019][131794] Num frames 9000...
|
1935 |
+
[2023-08-17 13:03:09,074][131794] Avg episode rewards: #0: 36.173, true rewards: #0: 15.007
|
1936 |
+
[2023-08-17 13:03:09,074][131794] Avg episode reward: 36.173, avg true_objective: 15.007
|
1937 |
+
[2023-08-17 13:03:09,127][131794] Num frames 9100...
|
1938 |
+
[2023-08-17 13:03:09,181][131794] Num frames 9200...
|
1939 |
+
[2023-08-17 13:03:09,235][131794] Num frames 9300...
|
1940 |
+
[2023-08-17 13:03:09,290][131794] Num frames 9400...
|
1941 |
+
[2023-08-17 13:03:09,344][131794] Num frames 9500...
|
1942 |
+
[2023-08-17 13:03:09,398][131794] Num frames 9600...
|
1943 |
+
[2023-08-17 13:03:09,452][131794] Num frames 9700...
|
1944 |
+
[2023-08-17 13:03:09,506][131794] Num frames 9800...
|
1945 |
+
[2023-08-17 13:03:09,559][131794] Num frames 9900...
|
1946 |
+
[2023-08-17 13:03:09,663][131794] Avg episode rewards: #0: 34.137, true rewards: #0: 14.280
|
1947 |
+
[2023-08-17 13:03:09,664][131794] Avg episode reward: 34.137, avg true_objective: 14.280
|
1948 |
+
[2023-08-17 13:03:09,667][131794] Num frames 10000...
|
1949 |
+
[2023-08-17 13:03:09,720][131794] Num frames 10100...
|
1950 |
+
[2023-08-17 13:03:09,775][131794] Num frames 10200...
|
1951 |
+
[2023-08-17 13:03:09,831][131794] Num frames 10300...
|
1952 |
+
[2023-08-17 13:03:09,887][131794] Num frames 10400...
|
1953 |
+
[2023-08-17 13:03:09,942][131794] Num frames 10500...
|
1954 |
+
[2023-08-17 13:03:09,997][131794] Num frames 10600...
|
1955 |
+
[2023-08-17 13:03:10,101][131794] Avg episode rewards: #0: 32.115, true rewards: #0: 13.365
|
1956 |
+
[2023-08-17 13:03:10,102][131794] Avg episode reward: 32.115, avg true_objective: 13.365
|
1957 |
+
[2023-08-17 13:03:10,108][131794] Num frames 10700...
|
1958 |
+
[2023-08-17 13:03:10,164][131794] Num frames 10800...
|
1959 |
+
[2023-08-17 13:03:10,220][131794] Num frames 10900...
|
1960 |
+
[2023-08-17 13:03:10,275][131794] Num frames 11000...
|
1961 |
+
[2023-08-17 13:03:10,334][131794] Avg episode rewards: #0: 29.235, true rewards: #0: 12.236
|
1962 |
+
[2023-08-17 13:03:10,335][131794] Avg episode reward: 29.235, avg true_objective: 12.236
|
1963 |
+
[2023-08-17 13:03:10,387][131794] Num frames 11100...
|
1964 |
+
[2023-08-17 13:03:10,442][131794] Num frames 11200...
|
1965 |
+
[2023-08-17 13:03:10,497][131794] Num frames 11300...
|
1966 |
+
[2023-08-17 13:03:10,553][131794] Num frames 11400...
|
1967 |
+
[2023-08-17 13:03:10,610][131794] Num frames 11500...
|
1968 |
+
[2023-08-17 13:03:10,666][131794] Num frames 11600...
|
1969 |
+
[2023-08-17 13:03:10,720][131794] Num frames 11700...
|
1970 |
+
[2023-08-17 13:03:10,779][131794] Num frames 11800...
|
1971 |
+
[2023-08-17 13:03:10,862][131794] Avg episode rewards: #0: 28.046, true rewards: #0: 11.846
|
1972 |
+
[2023-08-17 13:03:10,863][131794] Avg episode reward: 28.046, avg true_objective: 11.846
|
1973 |
+
[2023-08-17 13:03:22,380][131794] Replay video saved to /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/replay.mp4!
|