Initial commit
Browse files- .gitattributes +1 -0
- README.md +57 -0
- args.yml +65 -0
- config.yml +7 -0
- env_kwargs.yml +1 -0
- replay.mp4 +3 -0
- results.json +1 -0
- td3-Ant-v3.zip +3 -0
- td3-Ant-v3/_stable_baselines3_version +1 -0
- td3-Ant-v3/actor.optimizer.pth +3 -0
- td3-Ant-v3/critic.optimizer.pth +3 -0
- td3-Ant-v3/data +110 -0
- td3-Ant-v3/policy.pth +3 -0
- td3-Ant-v3/pytorch_variables.pth +3 -0
- td3-Ant-v3/system_info.txt +7 -0
- train_eval_metrics.zip +3 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- Ant-v3
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: TD3
|
10 |
+
results:
|
11 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: 5822.96 +/- 93.33
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: Ant-v3
|
20 |
+
type: Ant-v3
|
21 |
+
---
|
22 |
+
|
23 |
+
# **TD3** Agent playing **Ant-v3**
|
24 |
+
This is a trained model of a **TD3** agent playing **Ant-v3**
|
25 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
|
26 |
+
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
|
27 |
+
|
28 |
+
The RL Zoo is a training framework for Stable Baselines3
|
29 |
+
reinforcement learning agents,
|
30 |
+
with hyperparameter optimization and pre-trained agents included.
|
31 |
+
|
32 |
+
## Usage (with SB3 RL Zoo)
|
33 |
+
|
34 |
+
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
|
35 |
+
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
|
36 |
+
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
|
37 |
+
|
38 |
+
```
|
39 |
+
# Download model and save it into the logs/ folder
|
40 |
+
python -m utils.load_from_hub --algo td3 --env Ant-v3 -orga sb3 -f logs/
|
41 |
+
python enjoy.py --algo td3 --env Ant-v3 -f logs/
|
42 |
+
```
|
43 |
+
|
44 |
+
## Training (with the RL Zoo)
|
45 |
+
```
|
46 |
+
python train.py --algo td3 --env Ant-v3 -f logs/
|
47 |
+
# Upload the model and generate video (when possible)
|
48 |
+
python -m utils.push_to_hub --algo td3 --env Ant-v3 -f logs/ -orga sb3
|
49 |
+
```
|
50 |
+
|
51 |
+
## Hyperparameters
|
52 |
+
```python
|
53 |
+
OrderedDict([('learning_starts', 10000),
|
54 |
+
('n_timesteps', 1000000.0),
|
55 |
+
('policy', 'MlpPolicy'),
|
56 |
+
('normalize', False)])
|
57 |
+
```
|
args.yml
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - algo
|
3 |
+
- td3
|
4 |
+
- - env
|
5 |
+
- Ant-v3
|
6 |
+
- - env_kwargs
|
7 |
+
- null
|
8 |
+
- - eval_episodes
|
9 |
+
- 20
|
10 |
+
- - eval_freq
|
11 |
+
- 10000
|
12 |
+
- - gym_packages
|
13 |
+
- []
|
14 |
+
- - hyperparams
|
15 |
+
- null
|
16 |
+
- - log_folder
|
17 |
+
- logs/
|
18 |
+
- - log_interval
|
19 |
+
- 10
|
20 |
+
- - n_eval_envs
|
21 |
+
- 5
|
22 |
+
- - n_evaluations
|
23 |
+
- 20
|
24 |
+
- - n_jobs
|
25 |
+
- 1
|
26 |
+
- - n_startup_trials
|
27 |
+
- 10
|
28 |
+
- - n_timesteps
|
29 |
+
- -1
|
30 |
+
- - n_trials
|
31 |
+
- 10
|
32 |
+
- - no_optim_plots
|
33 |
+
- false
|
34 |
+
- - num_threads
|
35 |
+
- 2
|
36 |
+
- - optimization_log_path
|
37 |
+
- null
|
38 |
+
- - optimize_hyperparameters
|
39 |
+
- false
|
40 |
+
- - pruner
|
41 |
+
- median
|
42 |
+
- - sampler
|
43 |
+
- tpe
|
44 |
+
- - save_freq
|
45 |
+
- -1
|
46 |
+
- - save_replay_buffer
|
47 |
+
- false
|
48 |
+
- - seed
|
49 |
+
- 594371
|
50 |
+
- - storage
|
51 |
+
- null
|
52 |
+
- - study_name
|
53 |
+
- null
|
54 |
+
- - tensorboard_log
|
55 |
+
- ''
|
56 |
+
- - trained_agent
|
57 |
+
- ''
|
58 |
+
- - truncate_last_trajectory
|
59 |
+
- true
|
60 |
+
- - uuid
|
61 |
+
- true
|
62 |
+
- - vec_env
|
63 |
+
- dummy
|
64 |
+
- - verbose
|
65 |
+
- 1
|
config.yml
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - learning_starts
|
3 |
+
- 10000
|
4 |
+
- - n_timesteps
|
5 |
+
- 1000000.0
|
6 |
+
- - policy
|
7 |
+
- MlpPolicy
|
env_kwargs.yml
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:718890192d0be756a7866351f0faab73a186cf49e7c283dbbec5095805cd88fc
|
3 |
+
size 1555914
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 5822.9598441, "std_reward": 93.33450301420302, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T16:33:36.782278"}
|
td3-Ant-v3.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fe8d8fab4bdf2253c738c1afbc98992b1824abfa729176df899572189a103f1
|
3 |
+
size 8122729
|
td3-Ant-v3/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.1a8
|
td3-Ant-v3/actor.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:908af03ae826e8f8b9146031bdc634cfefc5c77e34f3d7fa635460ad12198b93
|
3 |
+
size 1343361
|
td3-Ant-v3/critic.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00d3311090610c43fd4d0f7d08a17f5e826572b57711c028471f71283edecb99
|
3 |
+
size 2704029
|
td3-Ant-v3/data
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnRkMy5wb2xpY2llc5SMCVREM1BvbGljeZSTlC4=",
|
5 |
+
"__module__": "stable_baselines3.td3.policies",
|
6 |
+
"__doc__": "\n Policy class (with both actor and critic) for TD3.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n :param n_critics: Number of critic networks to create.\n :param share_features_extractor: Whether to share or not the features extractor\n between the actor and the critic (this saves computation time)\n ",
|
7 |
+
"__init__": "<function TD3Policy.__init__ at 0x7fcd4de76170>",
|
8 |
+
"_build": "<function TD3Policy._build at 0x7fcd4de76200>",
|
9 |
+
"_get_constructor_parameters": "<function TD3Policy._get_constructor_parameters at 0x7fcd4de76290>",
|
10 |
+
"make_actor": "<function TD3Policy.make_actor at 0x7fcd4de76320>",
|
11 |
+
"make_critic": "<function TD3Policy.make_critic at 0x7fcd4de763b0>",
|
12 |
+
"forward": "<function TD3Policy.forward at 0x7fcd4de76440>",
|
13 |
+
"_predict": "<function TD3Policy._predict at 0x7fcd4de764d0>",
|
14 |
+
"set_training_mode": "<function TD3Policy.set_training_mode at 0x7fcd4de76560>",
|
15 |
+
"__abstractmethods__": "frozenset()",
|
16 |
+
"_abc_impl": "<_abc_data object at 0x7fcd4de741b0>"
|
17 |
+
},
|
18 |
+
"verbose": 1,
|
19 |
+
"policy_kwargs": {},
|
20 |
+
"observation_space": {
|
21 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
22 |
+
":serialized:": "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",
|
23 |
+
"dtype": "float64",
|
24 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]",
|
25 |
+
"high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf]",
|
26 |
+
"bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False]",
|
27 |
+
"bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False]",
|
28 |
+
"_np_random": null,
|
29 |
+
"_shape": [
|
30 |
+
111
|
31 |
+
]
|
32 |
+
},
|
33 |
+
"action_space": {
|
34 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
35 |
+
":serialized:": "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",
|
36 |
+
"dtype": "float32",
|
37 |
+
"low": "[-1. -1. -1. -1. -1. -1. -1. -1.]",
|
38 |
+
"high": "[1. 1. 1. 1. 1. 1. 1. 1.]",
|
39 |
+
"bounded_below": "[ True True True True True True True True]",
|
40 |
+
"bounded_above": "[ True True True True True True True True]",
|
41 |
+
"_np_random": "RandomState(MT19937)",
|
42 |
+
"_shape": [
|
43 |
+
8
|
44 |
+
]
|
45 |
+
},
|
46 |
+
"n_envs": 1,
|
47 |
+
"num_timesteps": 1000876,
|
48 |
+
"_total_timesteps": 1000000,
|
49 |
+
"_num_timesteps_at_start": 0,
|
50 |
+
"seed": 0,
|
51 |
+
"action_noise": null,
|
52 |
+
"start_time": 1635497836.4815102,
|
53 |
+
"learning_rate": 0.001,
|
54 |
+
"tensorboard_log": null,
|
55 |
+
"lr_schedule": {
|
56 |
+
":type:": "<class 'function'>",
|
57 |
+
":serialized:": "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"
|
58 |
+
},
|
59 |
+
"_last_obs": null,
|
60 |
+
"_last_episode_starts": {
|
61 |
+
":type:": "<class 'numpy.ndarray'>",
|
62 |
+
":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQGUdJRiLg=="
|
63 |
+
},
|
64 |
+
"_last_original_obs": {
|
65 |
+
":type:": "<class 'numpy.ndarray'>",
|
66 |
+
":serialized:": "gASVBQQAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLb4aUaAOMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUJ4AwAAYM0u1KqJ5T+euT3eX9btPzHhEPPb9rC/4zH3hL1TxL/mOdEjhlbUP8UZyi6t6tE/4mdN1EZb4D+rH2hhd8zgv0O7bm2it+C/UATuInEL27/ZoEu+LWrgv4c0UQaquN0/PdlS81uO4D8l5qgs8cAVQEg6zjCzPdy/d2pmbz0W3j/Yx4Z9owbjP1D3fGgqHcY/RO88Cy+N1r+d96rmi8oTwDTBo1iP59g/3Yx6TbgyfL+aPbDX0IlxP2I8edj8YwVAzDiUxaYe2L8MDm9dkZ4XQBs81O0d+bg/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlHSUYi4="
|
67 |
+
},
|
68 |
+
"_episode_num": 1221,
|
69 |
+
"use_sde": false,
|
70 |
+
"sde_sample_freq": -1,
|
71 |
+
"_current_progress_remaining": -0.0008760000000000989,
|
72 |
+
"ep_info_buffer": {
|
73 |
+
":type:": "<class 'collections.deque'>",
|
74 |
+
":serialized:": "gASVgBAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIHeT1YPYKt0CUhpRSlIwBbJRN6AOMAXSUR0DAvpEkSmIkdX2UKGgGaAloD0MIImx4egETtUCUhpRSlGgVTegDaBZHQMDCyhLf1pV1fZQoaAZoCWgPQwhREaeT7E63QJSGlFKUaBVN6ANoFkdAwMbfhESdv3V9lChoBmgJaA9DCEXXhR/s8bVAlIaUUpRoFU3oA2gWR0DAyvXkJa7mdX2UKGgGaAloD0MIeSPzyB9FtkCUhpRSlGgVTegDaBZHQMDPC8Swnpl1fZQoaAZoCWgPQwjqdvaVC6+2QJSGlFKUaBVN6ANoFkdAwNMihNdqtnV9lChoBmgJaA9DCPbQPlbkAbdAlIaUUpRoFU3oA2gWR0DA3etupCKKdX2UKGgGaAloD0MINPW6RcCxtkCUhpRSlGgVTegDaBZHQMDiE8nNPgx1fZQoaAZoCWgPQwhwXMZNwX22QJSGlFKUaBVN6ANoFkdAwOY/QN0/4nV9lChoBmgJaA9DCHDurx4P+7ZAlIaUUpRoFU3oA2gWR0DA6lWh24d7dX2UKGgGaAloD0MIHogs0nhet0CUhpRSlGgVTegDaBZHQMDubENnXd11fZQoaAZoCWgPQwgWak3z5te2QJSGlFKUaBVN6ANoFkdAwPKD7w8W9HV9lChoBmgJaA9DCCo5J/a8qbdAlIaUUpRoFU3oA2gWR0DA9pqkqMFVdX2UKGgGaAloD0MItWtCWnc3t0CUhpRSlGgVTegDaBZHQMD6sSQYDT11fZQoaAZoCWgPQwhseHqlcCK3QJSGlFKUaBVN6ANoFkdAwP7Ief7Jn3V9lChoBmgJaA9DCJJdaRl9vrVAlIaUUpRoFU3oA2gWR0DBAuzjLjgidX2UKGgGaAloD0MINCvbh1irtkCUhpRSlGgVTegDaBZHQMENyfNRm9R1fZQoaAZoCWgPQwjV52orPnG2QJSGlFKUaBVN6ANoFkdAwRHgp0fYBnV9lChoBmgJaA9DCN9OIsKHhLZAlIaUUpRoFU3oA2gWR0DBFfbP8hs7dX2UKGgGaAloD0MIp8mMt/GItkCUhpRSlGgVTegDaBZHQMEaDTZ6D5F1fZQoaAZoCWgPQwjQtMTKUCK3QJSGlFKUaBVN6ANoFkdAwR4kYoAn2XV9lChoBmgJaA9DCPZ9OEjMq7ZAlIaUUpRoFU3oA2gWR0DBIjnnyNGWdX2UKGgGaAloD0MInrXbLlzmtUCUhpRSlGgVTegDaBZHQMEmWUUGmk51fZQoaAZoCWgPQwj9ZmK6gK63QJSGlFKUaBVN6ANoFkdAwSqGQJXyRXV9lChoBmgJaA9DCAZINIG62rZAlIaUUpRoFU3oA2gWR0DBLp1ix3V1dX2UKGgGaAloD0MI5h99kx6ptkCUhpRSlGgVTegDaBZHQMEys2sJY1Z1fZQoaAZoCWgPQwhTspyEKha3QJSGlFKUaBVN6ANoFkdAwT1+GPgeinV9lChoBmgJaA9DCHB4QUTuJrdAlIaUUpRoFU3oA2gWR0DBQZYOrhitdX2UKGgGaAloD0MIGavN/wtDt0CUhpRSlGgVTegDaBZHQMFFt7ngYP51fZQoaAZoCWgPQwi6n1OQX/+2QJSGlFKUaBVN6ANoFkdAwUnjEYwZfnV9lChoBmgJaA9DCO3w12T5krdAlIaUUpRoFU3oA2gWR0DBTgVOuaF3dX2UKGgGaAloD0MI2c9iKZaLtkCUhpRSlGgVTegDaBZHQMFSHAl4TsZ1fZQoaAZoCWgPQwjmzkwwnARsQJSGlFKUaBVLOmgWR0DBVaJavA45dX2UKGgGaAloD0MI3eukvkw6t0CUhpRSlGgVTegDaBZHQMFWb4Oc2BJ1fZQoaAZoCWgPQwhVUbzKQh+3QJSGlFKUaBVN6ANoFkdAwVqIMm4RVnV9lChoBmgJaA9DCOJa7WF35LZAlIaUUpRoFU3oA2gWR0DBXqAmXw9adX2UKGgGaAloD0MI83aE0w5RtkCUhpRSlGgVTegDaBZHQMFiwx1oxpN1fZQoaAZoCWgPQwjJBWfwP4m2QJSGlFKUaBVN6ANoFkdAwW2XbqQiinV9lChoBmgJaA9DCKNWmL6XOYHAlIaUUpRoFU3oA2gWR0DBcba8WbgCdX2UKGgGaAloD0MINdO9Ti7BtUCUhpRSlGgVTegDaBZHQMF1zj6Fds11fZQoaAZoCWgPQwhrm+Jx2ai2QJSGlFKUaBVN6ANoFkdAwXnkrGza9XV9lChoBmgJaA9DCL+4VKWFMKZAlIaUUpRoFU0DAmgWR0DBfa/rnkksdX2UKGgGaAloD0MIPiZSms1fb0CUhpRSlGgVTegDaBZHQMGAHe0w8GN1fZQoaAZoCWgPQwi45LhTzk22QJSGlFKUaBVN6ANoFkdAwYRAjrRjSXV9lChoBmgJaA9DCKxxNh2Z4LdAlIaUUpRoFU3oA2gWR0DBiGNJFspHdX2UKGgGaAloD0MIOl0WE5uBtkCUhpRSlGgVTegDaBZHQMGMgS13MZB1fZQoaAZoCWgPQwhH5/wUb2e3QJSGlFKUaBVN6ANoFkdAwZCyZiuuBHV9lChoBmgJaA9DCGrAIOmf6rZAlIaUUpRoFU3oA2gWR0DBm3KnivPkdX2UKGgGaAloD0MII93PKdCptkCUhpRSlGgVTegDaBZHQMGfiMDW9UV1fZQoaAZoCWgPQwjYZfhPD2i2QJSGlFKUaBVN6ANoFkdAwaOntv4ub3V9lChoBmgJaA9DCM/b2Ox4cLFAlIaUUpRoFU30AmgWR0DBp5dzOopAdX2UKGgGaAloD0MIEodsIK2atkCUhpRSlGgVTegDaBZHQMGq014gRsd1fZQoaAZoCWgPQwg+INCZ5Bm3QJSGlFKUaBVN6ANoFkdAwa7yYplSTHV9lChoBmgJaA9DCCOkbmejjLZAlIaUUpRoFU3oA2gWR0DBsxy99MK1dX2UKGgGaAloD0MIeH3mrBM8t0CUhpRSlGgVTegDaBZHQMG3M7oB7u51fZQoaAZoCWgPQwiNYU7QRka2QJSGlFKUaBVN6ANoFkdAwbtI4YJmd3V9lChoBmgJaA9DCOOJIM6TLLdAlIaUUpRoFU3oA2gWR0DBv17fR/mUdX2UKGgGaAloD0MIyvs4mrNMtkCUhpRSlGgVTegDaBZHQMHKLKEvkBF1fZQoaAZoCWgPQwixhovcuwe3QJSGlFKUaBVN6ANoFkdAwc5EBDohZHV9lChoBmgJaA9DCD4FwHgS5rZAlIaUUpRoFU3oA2gWR0DB0nA9RrJsdX2UKGgGaAloD0MIsDcxJPOmt0CUhpRSlGgVTegDaBZHQMHWk7btZ3d1fZQoaAZoCWgPQwiqfqXztU22QJSGlFKUaBVN6ANoFkdAwdq3vAGjbnV9lChoBmgJaA9DCKOTpdbzVbdAlIaUUpRoFU3oA2gWR0DB3s7lNlAedX2UKGgGaAloD0MIBVCMLNEIt0CUhpRSlGgVTegDaBZHQMHi6ZIpYtB1fZQoaAZoCWgPQwhxr8xbXcC2QJSGlFKUaBVN6ANoFkdAweb+RChN/XV9lChoBmgJaA9DCODyWDN2MrZAlIaUUpRoFU3oA2gWR0DB6xQ2jwhGdX2UKGgGaAloD0MIONpxw/MAuECUhpRSlGgVTegDaBZHQMHvK8wYced1fZQoaAZoCWgPQwj0Fg/vffG2QJSGlFKUaBVN6ANoFkdAwfnzjyWiUXV9lChoBmgJaA9DCM9LxcbYQbdAlIaUUpRoFU3oA2gWR0DB/gj+kxh2dX2UKGgGaAloD0MINlt5yUsit0CUhpRSlGgVTegDaBZHQMICHk5hjON1fZQoaAZoCWgPQwgIkncO1ZK1QJSGlFKUaBVN6ANoFkdAwgZA4xUNrnV9lChoBmgJaA9DCIXRrGw7RLdAlIaUUpRoFU3oA2gWR0DCClZqASWadX2UKGgGaAloD0MIAizy6+MLuECUhpRSlGgVTegDaBZHQMIObETQE6l1fZQoaAZoCWgPQwg3cAfqdCmcQJSGlFKUaBVNWQFoFkdAwhInwNLDh3V9lChoBmgJaA9DCGZJgJoyT7dAlIaUUpRoFU3oA2gWR0DCE/Vld1MedX2UKGgGaAloD0MI0lJ5O6ZOt0CUhpRSlGgVTegDaBZHQMIYKKlHjId1fZQoaAZoCWgPQwhTBDi927m3QJSGlFKUaBVN6ANoFkdAwhw+N96Tn3V9lChoBmgJaA9DCEc+r3jiordAlIaUUpRoFU3oA2gWR0DCIFUkdFOPdX2UKGgGaAloD0MIr5Y7M5H2t0CUhpRSlGgVTegDaBZHQMIrIV/c32p1fZQoaAZoCWgPQwim7V9Z8Va2QJSGlFKUaBVN6ANoFkdAwi9J1wHZ9XV9lChoBmgJaA9DCDTaqiQS+aBAlIaUUpRoFU25AWgWR0DCMxmZZ0SzdX2UKGgGaAloD0MId0gxQCLftkCUhpRSlGgVTegDaBZHQMI1PaNEPUd1fZQoaAZoCWgPQwgX9UnufNC2QJSGlFKUaBVN6ANoFkdAwjlt+5vtMXV9lChoBmgJaA9DCPBRf70GALdAlIaUUpRoFU3oA2gWR0DCPYZUxVQzdX2UKGgGaAloD0MIDRmPUnkHt0CUhpRSlGgVTegDaBZHQMJBnKVII4V1fZQoaAZoCWgPQwgyk6gXPO+1QJSGlFKUaBVN6ANoFkdAwkW6l9BrvnV9lChoBmgJaA9DCDSEY5btfrVAlIaUUpRoFU3oA2gWR0DCSdIFkhA4dX2UKGgGaAloD0MIukvirOi8t0CUhpRSlGgVTegDaBZHQMJN6Jmukk91fZQoaAZoCWgPQwhOKhprL/S3QJSGlFKUaBVN6ANoFkdAwlH/w++ueXV9lChoBmgJaA9DCMQhG0i3vbZAlIaUUpRoFU3oA2gWR0DCXMQPPLPldX2UKGgGaAloD0MIR68GKMmOtUCUhpRSlGgVTegDaBZHQMJg4ANgBtF1fZQoaAZoCWgPQwhi9x3Da/G2QJSGlFKUaBVN6ANoFkdAwmUB3+uNgnV9lChoBmgJaA9DCEjcY+nHibZAlIaUUpRoFU3oA2gWR0DCaRbXtjTbdX2UKGgGaAloD0MIs+20NW4WuECUhpRSlGgVTegDaBZHQMJtK+O4oZ11fZQoaAZoCWgPQwgHl445D2O3QJSGlFKUaBVN6ANoFkdAwnFA33pOe3V9lChoBmgJaA9DCJ1/u+wPqrZAlIaUUpRoFU3oA2gWR0DCdVZ4lhPTdX2UKGgGaAloD0MIOq3boF6htkCUhpRSlGgVTegDaBZHQMJ5clvIfbN1fZQoaAZoCWgPQwi77xgeG1O2QJSGlFKUaBVN6ANoFkdAwn2r3jdYXHV9lChoBmgJaA9DCG/0MR9oVrdAlIaUUpRoFU3oA2gWR0DCgcVGI9DAdX2UKGgGaAloD0MImfT3Upi+tkCUhpRSlGgVTegDaBZHQMKMkJh4MWp1ZS4="
|
75 |
+
},
|
76 |
+
"ep_success_buffer": {
|
77 |
+
":type:": "<class 'collections.deque'>",
|
78 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
79 |
+
},
|
80 |
+
"_n_updates": 991254,
|
81 |
+
"buffer_size": 1,
|
82 |
+
"batch_size": 100,
|
83 |
+
"learning_starts": 10000,
|
84 |
+
"tau": 0.005,
|
85 |
+
"gamma": 0.99,
|
86 |
+
"gradient_steps": -1,
|
87 |
+
"optimize_memory_usage": false,
|
88 |
+
"replay_buffer_class": {
|
89 |
+
":type:": "<class 'abc.ABCMeta'>",
|
90 |
+
":serialized:": "gASVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
91 |
+
"__module__": "stable_baselines3.common.buffers",
|
92 |
+
"__doc__": "\n Replay buffer used in off-policy algorithms like SAC/TD3.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device:\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n of the replay buffer which reduces by almost a factor two the memory used,\n at a cost of more complexity.\n See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n separately and treat the task as infinite horizon task.\n https://github.com/DLR-RM/stable-baselines3/issues/284\n ",
|
93 |
+
"__init__": "<function ReplayBuffer.__init__ at 0x7fcd4e2f3b90>",
|
94 |
+
"add": "<function ReplayBuffer.add at 0x7fcd4e2f3c20>",
|
95 |
+
"sample": "<function ReplayBuffer.sample at 0x7fcd4de5a7a0>",
|
96 |
+
"_get_samples": "<function ReplayBuffer._get_samples at 0x7fcd4de5a830>",
|
97 |
+
"__abstractmethods__": "frozenset()",
|
98 |
+
"_abc_impl": "<_abc_data object at 0x7fcd4e34b5d0>"
|
99 |
+
},
|
100 |
+
"replay_buffer_kwargs": {},
|
101 |
+
"train_freq": {
|
102 |
+
":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
|
103 |
+
":serialized:": "gASVZAAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMB2VwaXNvZGWUhZRSlIaUgZQu"
|
104 |
+
},
|
105 |
+
"use_sde_at_warmup": false,
|
106 |
+
"policy_delay": 2,
|
107 |
+
"target_noise_clip": 0.5,
|
108 |
+
"target_policy_noise": 0.2,
|
109 |
+
"remove_time_limit_termination": false
|
110 |
+
}
|
td3-Ant-v3/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:faca386889a455c0c848c8e33dafe9d1ed02bdb3d15ce6cf4a8b62c5ca0d2c24
|
3 |
+
size 4049721
|
td3-Ant-v3/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
td3-Ant-v3/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.13.0-44-generic-x86_64-with-debian-bullseye-sid #49~20.04.1-Ubuntu SMP Wed May 18 18:44:28 UTC 2022
|
2 |
+
Python: 3.7.10
|
3 |
+
Stable-Baselines3: 1.5.1a8
|
4 |
+
PyTorch: 1.11.0
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.2
|
7 |
+
Gym: 0.21.0
|
train_eval_metrics.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79b91b69452a6596f1de58fe50f234dfd9f08cd1f720d2a522698e56819b7c13
|
3 |
+
size 69187
|