Hugging Face's logo

sb3
/
a2c-BipedalWalkerHardcore-v3

Reinforcement Learning
stable-baselines3
BipedalWalkerHardcore-v3
deep-reinforcement-learning
Eval Results
Model card Files Community
araffin commited on
Commit
b5b2438
·
1 Parent(s): d5b0594

Initial commit

Browse files
Files changed (16) hide show
  1. .gitattributes +2 -0
  2. README.md +69 -0
  3. a2c-BipedalWalkerHardcore-v3.zip +3 -0
  4. a2c-BipedalWalkerHardcore-v3/_stable_baselines3_version +1 -0
  5. a2c-BipedalWalkerHardcore-v3/data +106 -0
  6. a2c-BipedalWalkerHardcore-v3/policy.optimizer.pth +3 -0
  7. a2c-BipedalWalkerHardcore-v3/policy.pth +3 -0
  8. a2c-BipedalWalkerHardcore-v3/pytorch_variables.pth +3 -0
  9. a2c-BipedalWalkerHardcore-v3/system_info.txt +7 -0
  10. args.yml +59 -0
  11. config.yml +31 -0
  12. env_kwargs.yml +1 -0
  13. replay.mp4 +3 -0
  14. results.json +1 -0
  15. train_eval_metrics.zip +3 -0
  16. vec_normalize.pkl +3 -0
.gitattributes CHANGED
@@ -25,3 +25,5 @@ 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
29
+ vec_normalize.pkl filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - BipedalWalkerHardcore-v3
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ model-index:
9
+ - name: A2C
10
+ results:
11
+ - metrics:
12
+ - type: mean_reward
13
+ value: 135.60 +/- 128.48
14
+ name: mean_reward
15
+ task:
16
+ type: reinforcement-learning
17
+ name: reinforcement-learning
18
+ dataset:
19
+ name: BipedalWalkerHardcore-v3
20
+ type: BipedalWalkerHardcore-v3
21
+ ---
22
+
23
+ # **A2C** Agent playing **BipedalWalkerHardcore-v3**
24
+ This is a trained model of a **A2C** agent playing **BipedalWalkerHardcore-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 a2c --env BipedalWalkerHardcore-v3 -orga sb3 -f logs/
41
+ python enjoy.py --algo a2c --env BipedalWalkerHardcore-v3 -f logs/
42
+ ```
43
+
44
+ ## Training (with the RL Zoo)
45
+ ```
46
+ python train.py --algo a2c --env BipedalWalkerHardcore-v3 -f logs/
47
+ # Upload the model and generate video (when possible)
48
+ python -m utils.push_to_hub --algo a2c --env BipedalWalkerHardcore-v3 -f logs/ -orga sb3
49
+ ```
50
+
51
+ ## Hyperparameters
52
+ ```python
53
+ OrderedDict([('ent_coef', 0.001),
54
+ ('gae_lambda', 0.9),
55
+ ('gamma', 0.99),
56
+ ('learning_rate', 'lin_0.0008'),
57
+ ('max_grad_norm', 0.5),
58
+ ('n_envs', 32),
59
+ ('n_steps', 8),
60
+ ('n_timesteps', 200000000.0),
61
+ ('normalize', True),
62
+ ('normalize_advantage', False),
63
+ ('policy', 'MlpPolicy'),
64
+ ('policy_kwargs', 'dict(log_std_init=-2, ortho_init=False)'),
65
+ ('use_rms_prop', True),
66
+ ('use_sde', True),
67
+ ('vf_coef', 0.4),
68
+ ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
69
+ ```
a2c-BipedalWalkerHardcore-v3.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77c7f06a39273c54ccd9f83dbd2b697bb973bb1fd05636d30cdded26cee298df
3
+ size 130172
a2c-BipedalWalkerHardcore-v3/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.5.1a8
a2c-BipedalWalkerHardcore-v3/data ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "policy_class": {
3
+ ":type:": "<class 'abc.ABCMeta'>",
4
+ ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
5
+ "__module__": "stable_baselines3.common.policies",
6
+ "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\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 ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\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 ",
7
+ "__init__": "<function ActorCriticPolicy.__init__ at 0x7f1abf2f5950>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f1abf2f59e0>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f1abf2f5a70>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f1abf2f5b00>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7f1abf2f5b90>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7f1abf2f5c20>",
13
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f1abf2f5cb0>",
14
+ "_predict": "<function ActorCriticPolicy._predict at 0x7f1abf2f5d40>",
15
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f1abf2f5dd0>",
16
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1abf2f5e60>",
17
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f1abf2f5ef0>",
18
+ "__abstractmethods__": "frozenset()",
19
+ "_abc_impl": "<_abc_data object at 0x7f1abf346840>"
20
+ },
21
+ "verbose": 1,
22
+ "policy_kwargs": {
23
+ ":type:": "<class 'dict'>",
24
+ ":serialized:": "gASVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu",
25
+ "log_std_init": -2,
26
+ "ortho_init": false,
27
+ "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
28
+ "optimizer_kwargs": {
29
+ "alpha": 0.99,
30
+ "eps": 1e-05,
31
+ "weight_decay": 0
32
+ }
33
+ },
34
+ "observation_space": {
35
+ ":type:": "<class 'gym.spaces.box.Box'>",
36
+ ":serialized:": "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",
37
+ "dtype": "float32",
38
+ "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]",
39
+ "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]",
40
+ "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]",
41
+ "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]",
42
+ "_np_random": null,
43
+ "_shape": [
44
+ 24
45
+ ]
46
+ },
47
+ "action_space": {
48
+ ":type:": "<class 'gym.spaces.box.Box'>",
49
+ ":serialized:": "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",
50
+ "dtype": "float32",
51
+ "low": "[-1. -1. -1. -1.]",
52
+ "high": "[1. 1. 1. 1.]",
53
+ "bounded_below": "[ True True True True]",
54
+ "bounded_above": "[ True True True True]",
55
+ "_np_random": "RandomState(MT19937)",
56
+ "_shape": [
57
+ 4
58
+ ]
59
+ },
60
+ "n_envs": 32,
61
+ "num_timesteps": 200000000,
62
+ "_total_timesteps": 200000000,
63
+ "_num_timesteps_at_start": 0,
64
+ "seed": 0,
65
+ "action_noise": null,
66
+ "start_time": 1614946037.849201,
67
+ "learning_rate": {
68
+ ":type:": "<class 'function'>",
69
+ ":serialized:": "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"
70
+ },
71
+ "tensorboard_log": null,
72
+ "lr_schedule": {
73
+ ":type:": "<class 'function'>",
74
+ ":serialized:": "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"
75
+ },
76
+ "_last_obs": null,
77
+ "_last_episode_starts": null,
78
+ "_last_original_obs": {
79
+ ":type:": "<class 'numpy.ndarray'>",
80
+ ":serialized:": "gASVjQwAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSyBLGIaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUIADAAAFw40O5QtZLfmq4o6PRKDvElXvD21/7a6dDpcPz+PHzsAAIA/3ZQEPZL8trrKk1o/M2uBOgAAgD9gsuE+iULkPps/7D5Tpvo+9roIP+M6Gj/IijU/bsxiP656cD8AAIA/ZOgzO2jAczeoUPi6oxKDvHCuvT3NHJA7ABJcP41BCbsAAIA/68IGPR8bkDvNfFo/qRtEuwAAgD9FsuE+bkLkPn8/7D41pvo+5roIP9A6Gj+yijU/UsxiP3uBcD8AAIA/q/IzO3xIMzdso7a6lBKDvO5svT0Q/lM76xpcPy1BmboAAIA/IWEGPcL7UzsigVo/Kz4QuwAAgD9LsuE+dELkPoU/7D47pvo+6boIP9U6Gj+3ijU/WMxiPwAAgD8AAIA/qeczO64beTfdxP26oxKDvAi0vT3+RpM7NBFcP1VKDrsAAIA/McoGPX5FkzuEfFo/nGpIuwAAgD9IsuE+cULkPoI/7D44pvo+57oIP9I6Gj+1ijU/VcxiP5KBcD8AAIA/hww0OzzEurc7AuM6HxKDvCsZvD2GyRW79D5cPyibSjsAAIA/8xgEPd/GFbs2mFo/nNzTOgAAgD9jsuE+jELkPp8/7D5Wpvo++LoIP+U6Gj/LijU/ccxiPwAAgD8AAIA/2Q80O780xTQg/0i4bxKDvLe/vD0VU+k4izJcPzxZrDoAAIA/72IFPXVH6Tg0jFo//7ueuAAAgD9asuE+g0LkPpU/7D5Mpvo+8roIP986Gj/DijU/aMxiPwAAgD8AAIA/XA00O3yRgrers546NhKDvJBIvD26btG6qDtcPydRKTsAAIA/k3gEPQlr0brQlFo/1ByUOgAAgD9gsuE+iULkPps/7D5Tpvo+9roIP+M6Gj/IijU/bsxiPwAAgD8AAIA/9As0O9iu17fuEwM7ExKDvDgAvD1w+iy7sEBcP0W9WzsAAIA/oeYDPT73LLsPmlo/tan0OgAAgD9jsuE+jELkPp8/7D5Wpvo++LoIP+U6Gj/LijU/ccxiPwAAgD8AAIA/guMzOxgkiTeMtAu7pxKDvO7MvT2CKKI7zw1cP7n1JbsAAIA/c+8GPQYnojvbelo/h6tcuwAAgD9IsuE+cULkPoI/7D44pvo+57oIP9I6Gj+1ijU/VcxiPwAAgD8AAIA/cfwzO5J49jYBFXu6ihKDvBY1vT3HtxE7jyJcP2BVv7kAAIA/kxAGPVG2ETuRhFo/cUvGugAAgD9RsuE+ekLkPow/7D5Cpvo+7boIP9k6Gj+8ijU/XsxiPwAAgD8AAIA/9Qk0O9PRFjYDn5m5dxKDvCPfvD2uTjI6Si5cP+MWYjoAAIA/d5AFPaNOMjpKilo/6KjyuQAAgD9asuE+g0LkPpU/7D5Mpvo+8roIP986Gj/DijU/aMxiP9B9cD8AAIA/kwA0O70exDbCyEe6hBKDvJobvT1E5Oc6ByZcP6vCc7YAAIA/IesFPSLi5zo2hlo/18edugAAgD9RsuE+ekLkPow/7D5Cpvo+7boIP9k6Gj+8ijU/XsxiPwAAgD8AAIA/Fw00Oy/irbeJWdM6JBKDvIAkvD17dAu7Ej5cP336QjsAAIA/YS4EPQFyC7t+l1o/ZT/FOgAAgD9jsuE+jELkPp8/7D5Wpvo++LoIP+U6Gj/LijU/ccxiP16ceT8AAIA/6Qs0O9Sj2rf73wQ7EhKDvN/9uz2OWS+72EBcP8h9XTsAAIA/4eADPXFWL7tAmlo/lwT4OgAAgD9msuE+j0LkPqI/7D5Zpvo++roIP+c6Gj/NijU/dMxiP2KceT8AAIA/uAs0OxQO9jXUn3q5dhKDvDLYvD0dcxE6Ri9cP+U2fDoAAIA/OYcFPeByETqfilo/qfvFuQAAgD9asuE+g0LkPpU/7D5Mpvo+8roIP986Gj/DijU/aMxiP699cD8AAIA/tAw0O6U6rbfejdI6JBKDvLokvD0S7gq7Ej5cP/CWQjsAAIA/1S4EPZ7rCruDl1o/T4HEOgAAgD9jsuE+jELkPp8/7D5Wpvo++LoIP+U6Gj/LijU/ccxiPwAAgD8AAIA/Jw00Oy7SmLe/v7k6LRKDvPA1vD0mIPW62zxcPziANjsAAIA/11EEPbAb9bo/llo/z1qtOgAAgD9msuE+j0LkPqI/7D5Zpvo++roIP+c6Gj/NijU/dMxiP2KceT8AAIA/quczOxYhejcdz/66pBKDvBq1vT2D4ZM7CRFcPzRAD7sAAIA/EcwGPQbgkztkfFo/5zxJuwAAgD9FsuE+bkLkPn8/7D41pvo+5roIP9A6Gj+yijU/UsxiPwAAgD8AAIA/+wQ0O04EijZbmgy6fRKDvKj+vD2sM6M6+ylcP3Wh2DkAAIA/9b4FPYYxozo6iFo/KxZeugAAgD9UsuE+fULkPo8/7D5Fpvo+77oIP9s6Gj++ijU/YcxiPwAAgD8AAIA/yg00Oz2JYbfUEIk6PRKDvMxXvD1w4bS6ijpcP7XGHjsAAIA/nZcEPSTetLqmk1o/INd/OgAAgD9gsuE+iULkPps/7D5Tpvo+9roIP+M6Gj/IijU/bsxiPwAAgD8AAIA/yQw0O6/SvzXoZ0O5dBKDvJ7RvD1e0OI5HjBcPw7ZijoAAIA/T30FPc3N4jkIi1o/P1aauQAAgD9asuE+g0LkPpU/7D5Mpvo+8roIP986Gj/DijU/aMxiP1GceT8AAIA/6gs0O9y84jUg9ma5cxKDvODVvD0kCgY6iC9cP/GkgjoAAIA/zYIFPV0JBjrmilo/E2u2uQAAgD9asuE+g0LkPpU/7D5Mpvo+8roIP986Gj/DijU/aMxiP6Z9cD8AAIA/9+kzO4FEbTfctfG6oRKDvMKovT11R4w7tBJcPwApA7sAAIA/57kGPfZFjDsmfVo/IOU+uwAAgD9FsuE+bkLkPn8/7D41pvo+5roIP9A6Gj+yijU/UsxiPwAAgD8AAIA/CvUzO4XsJzfcEau6khKDvApivT2ikEY7YhxcP6Xlg7oAAIA/o1EGPTmORjvCgVo/hhoHuwAAgD9LsuE+dELkPoU/7D47pvo+6boIP9U6Gj+3ijU/WMxiPz2ceT8AAIA/Iw00Ozr2kbddabE6MBKDvFU8vD2GH+q6WDxcP+1uMjsAAIA/O14EPT4b6rrClVo/3JKlOgAAgD9gsuE+iULkPps/7D5Tpvo+9roIP+M6Gj/IijU/bsxiPwB6cD8AAIA/YA00O+w9gbfaFp06NhKDvHJJvD0NTs+6nDtcP0uIKDsAAIA/TXsEPXFKz7qylFo/qZuSOgAAgD9gsuE+iULkPps/7D5Tpvo+9roIP+M6Gj/IijU/bsxiPwAAgD8AAIA/0w40O5vG/bbUOho6UxKDvCKCvD0GiEu6fDdcP5eOATsAAIA/i+sEPRCES7qukFo/LPAPOgAAgD9gsuE+iULkPps/7D5Tpvo+9roIP+M6Gj/IijU/bsxiPwAAgD8AAIA/LA80O1RP7rYh1BA6VBKDvJWFvD0MID+6LzdcP0CI/joAAIA/X/EEPZYcP7p0kFo/TyoHOgAAgD9gsuE+iULkPps/7D5Tpvo+9roIP+M6Gj/IijU/bsxiPwAAgD8AAIA/qAU0O0NWgDaaugK6fBKDvGr5vD3ovJc6sipcP/sU/TkAAIA/L7cFPTO8lzqjiFo/9X5OugAAgD9XsuE+gELkPpI/7D5Jpvo+8boIP906Gj/BijU/ZcxiP02ceT8AAIA/Hg80O7ii27YPewU6VhKDvIKJvD3/JTC69jZcP93/+DoAAIA/T/oEPV0jMLonkFo/aSb5OQAAgD9gsuE+iULkPps/7D5Tpvo+9roIP+M6Gj/IijU/bsxiPwAAgD8AAIA/DPkzO0DhDTckiZC6jRKDvB1IvT0VxCc78h9cPwnRJboAAIA/dSoGPUPCJzuLg1o/TUzkugAAgD9OsuE+d0LkPok/7D4/pvo+67oIP9c6Gj+6ijU/W8xiPwAAgD8AAIA/jA00O2tsgrfmhZ46NhKDvKZIvD1DMtG6njtcP+w6KTsAAIA/eXgEPYMu0brNlFo/EfKTOgAAgD9gsuE+iULkPps/7D5Tpvo+9roIP+M6Gj/IijU/bsxiP1R6cD8AAIA/lHSUYi4="
81
+ },
82
+ "_episode_num": 0,
83
+ "use_sde": true,
84
+ "sde_sample_freq": -1,
85
+ "_current_progress_remaining": 0.0,
86
+ "ep_info_buffer": {
87
+ ":type:": "<class 'collections.deque'>",
88
+ ":serialized:": "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"
89
+ },
90
+ "ep_success_buffer": {
91
+ ":type:": "<class 'collections.deque'>",
92
+ ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
93
+ },
94
+ "_n_updates": 781250,
95
+ "n_steps": 8,
96
+ "gamma": 0.99,
97
+ "gae_lambda": 0.9,
98
+ "ent_coef": 0.001,
99
+ "vf_coef": 0.4,
100
+ "max_grad_norm": 0.5,
101
+ "normalize_advantage": false,
102
+ "_last_dones": {
103
+ ":type:": "<class 'numpy.ndarray'>",
104
+ ":serialized:": "gASVqAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSyCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDIAABAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlHSUYi4="
105
+ }
106
+ }
a2c-BipedalWalkerHardcore-v3/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:208cdb8ce7f34209d740b8a38b3af3e2dadab10d417505a59492452345171be6
3
+ size 52094
a2c-BipedalWalkerHardcore-v3/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0affc04bd37aefe59e1a5167f4c76891df69a3cad5479eec5564b90cf3171952
3
+ size 52670
a2c-BipedalWalkerHardcore-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
a2c-BipedalWalkerHardcore-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
args.yml ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - a2c
4
+ - - env
5
+ - BipedalWalkerHardcore-v3
6
+ - - env_kwargs
7
+ - null
8
+ - - eval_episodes
9
+ - 10
10
+ - - eval_freq
11
+ - 50000
12
+ - - gym_packages
13
+ - []
14
+ - - hyperparams
15
+ - null
16
+ - - log_folder
17
+ - rl-trained-agents/
18
+ - - log_interval
19
+ - -1
20
+ - - n_evaluations
21
+ - 20
22
+ - - n_jobs
23
+ - 1
24
+ - - n_startup_trials
25
+ - 10
26
+ - - n_timesteps
27
+ - -1
28
+ - - n_trials
29
+ - 10
30
+ - - num_threads
31
+ - -1
32
+ - - optimize_hyperparameters
33
+ - false
34
+ - - pruner
35
+ - median
36
+ - - sampler
37
+ - tpe
38
+ - - save_freq
39
+ - -1
40
+ - - save_replay_buffer
41
+ - false
42
+ - - seed
43
+ - 2754640975
44
+ - - storage
45
+ - null
46
+ - - study_name
47
+ - null
48
+ - - tensorboard_log
49
+ - ''
50
+ - - trained_agent
51
+ - ''
52
+ - - truncate_last_trajectory
53
+ - true
54
+ - - uuid
55
+ - false
56
+ - - vec_env
57
+ - dummy
58
+ - - verbose
59
+ - 1
config.yml ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - ent_coef
3
+ - 0.001
4
+ - - gae_lambda
5
+ - 0.9
6
+ - - gamma
7
+ - 0.99
8
+ - - learning_rate
9
+ - lin_0.0008
10
+ - - max_grad_norm
11
+ - 0.5
12
+ - - n_envs
13
+ - 32
14
+ - - n_steps
15
+ - 8
16
+ - - n_timesteps
17
+ - 200000000.0
18
+ - - normalize
19
+ - true
20
+ - - normalize_advantage
21
+ - false
22
+ - - policy
23
+ - MlpPolicy
24
+ - - policy_kwargs
25
+ - dict(log_std_init=-2, ortho_init=False)
26
+ - - use_rms_prop
27
+ - true
28
+ - - use_sde
29
+ - true
30
+ - - vf_coef
31
+ - 0.4
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:c9c7afd547304917d946a2523127ad55cecbd4dca6c9dfd74e3736669c64702b
3
+ size 470808
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 135.60297590000002, "std_reward": 128.48213376377896, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T18:24:17.142610"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1befa9e31ffb04f84761a6055c35ca99a5054b67c340387eaa418b479038a82
3
+ size 5501161
vec_normalize.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bcc88ac9672ff00764c38be3e3e0ef1a09f0cfebf99a43df20e9daee641efcd
3
+ size 8096