jianzhnie commited on
Commit
569a1ce
1 Parent(s): 8409a9b

Initial commit

Browse files
README.md CHANGED
@@ -10,7 +10,7 @@ model-index:
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
- value: 233.30 +/- 154.48
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
 
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
+ value: 319.91 +/- 45.37
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
a2c-AntBulletEnv-v0.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f2306c3827c88bf725aabac539694f0d98982cbb20f9159cbda1f09bcc6dddb
3
- size 124828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d29e28a2ad9d57ab69917d65be0b5ed487a51b4a980d9926509422ddbc1d02f
3
+ size 124978
a2c-AntBulletEnv-v0/data CHANGED
@@ -4,19 +4,19 @@
4
  ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
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 0x7fee25290830>",
8
- "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fee252908c0>",
9
- "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fee25290950>",
10
- "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fee252909e0>",
11
- "_build": "<function ActorCriticPolicy._build at 0x7fee25290a70>",
12
- "forward": "<function ActorCriticPolicy.forward at 0x7fee25290b00>",
13
- "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fee25290b90>",
14
- "_predict": "<function ActorCriticPolicy._predict at 0x7fee25290c20>",
15
- "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fee25290cb0>",
16
- "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fee25290d40>",
17
- "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fee25290dd0>",
18
  "__abstractmethods__": "frozenset()",
19
- "_abc_impl": "<_abc_data object at 0x7fee2525ab40>"
20
  },
21
  "verbose": 1,
22
  "policy_kwargs": {
@@ -63,16 +63,16 @@
63
  "_num_timesteps_at_start": 0,
64
  "seed": null,
65
  "action_noise": null,
66
- "start_time": 1659060932.07266,
67
  "learning_rate": 0.00096,
68
- "tensorboard_log": "./tensorboard",
69
  "lr_schedule": {
70
  ":type:": "<class 'function'>",
71
- ":serialized:": "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"
72
  },
73
  "_last_obs": {
74
  ":type:": "<class 'numpy.ndarray'>",
75
- ":serialized:": "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"
76
  },
77
  "_last_episode_starts": {
78
  ":type:": "<class 'numpy.ndarray'>",
@@ -80,7 +80,7 @@
80
  },
81
  "_last_original_obs": {
82
  ":type:": "<class 'numpy.ndarray'>",
83
- ":serialized:": "gAWVNQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJbAAQAAAAAAAAAAAABw8fI1AACAPwAAAAAAAAAAAAAAAAAAAAAAAACAYnLavQAAAAAtGf+/AAAAAL8XSjwAAAAAz8D6PwAAAABW2089AAAAAE5y3T8AAAAAwRC+PQAAAADFq+q/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAkz0itgAAgD8AAAAAAAAAAAAAAAAAAAAAAAAAgGoTpbwAAAAAp3j3vwAAAAB8nsa9AAAAAImw5j8AAAAAm+pnPQAAAAB9Ct4/AAAAAHjnqT0AAAAAfr70vwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABGzILYAAIA/AAAAAAAAAAAAAAAAAAAAAAAAAIBSUk09AAAAAMoa6b8AAAAAr38sPQAAAACUDec/AAAAAFbYJ70AAAAA+K77PwAAAAAyCVg9AAAAALTD+L8AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAADeYQo3AACAPwAAAAAAAAAAAAAAAAAAAAAAAACA51VPvAAAAAD0d92/AAAAAGOSyj0AAAAAGbLjPwAAAADFAv09AAAAADL92j8AAAAAsGwCvgAAAAChvuy/AAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLHIaUjAFDlHSUUpQu"
84
  },
85
  "_episode_num": 0,
86
  "use_sde": true,
@@ -88,7 +88,7 @@
88
  "_current_progress_remaining": -0.1200000000000001,
89
  "ep_info_buffer": {
90
  ":type:": "<class 'collections.deque'>",
91
- ":serialized:": "gAWVZAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQB3yV8kUsWiMAWyUSxSMAXSURz/R5rxiG34LdX2UKGgGR0A4pthd+ocaaAdLLWgIRz/ZQuVX3g1ndWUu"
92
  },
93
  "ep_success_buffer": {
94
  ":type:": "<class 'collections.deque'>",
 
4
  ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
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 0x7f40275aedc0>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f40275aee50>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f40275aeee0>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f40275aef70>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7f40275b2040>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7f40275b20d0>",
13
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f40275b2160>",
14
+ "_predict": "<function ActorCriticPolicy._predict at 0x7f40275b21f0>",
15
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f40275b2280>",
16
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f40275b2310>",
17
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f40275b23a0>",
18
  "__abstractmethods__": "frozenset()",
19
+ "_abc_impl": "<_abc._abc_data object at 0x7f40276a8d00>"
20
  },
21
  "verbose": 1,
22
  "policy_kwargs": {
 
63
  "_num_timesteps_at_start": 0,
64
  "seed": null,
65
  "action_noise": null,
66
+ "start_time": 1659066388.5388026,
67
  "learning_rate": 0.00096,
68
+ "tensorboard_log": "work_dirs/AntBulletEnv-v0/tensorboard",
69
  "lr_schedule": {
70
  ":type:": "<class 'function'>",
71
+ ":serialized:": "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"
72
  },
73
  "_last_obs": {
74
  ":type:": "<class 'numpy.ndarray'>",
75
+ ":serialized:": "gAWVNQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJbAAQAAAAAAAJ/TlL9Gt2I+TwdhP2RMSDyQmgA+UZQZP80clr9zUu+9WhOCP0cZHD4eCn6+wrJQvigKw78DDcm9VzwQP6CV0D79s1K/ttrIPXXKmT6KfdY++xSiP78oOrwGbC4+gT5SvqqaOD/yAXU/+Wc6P2CIjz/HZ2m/sya5v6dz0L+Zdhy79hqcPuaHEz80XES/8zNeP1z9g78+9A4+rNc3v/pWdr7ZbHc/6s/DvQq7RL+rdL4+f2yJv4NKzT1Ekzm/5GhLPzDwnL9fKoi8hJ/HPgDncr6qmjg/8gF1P/lnOj9giI8/omDMvkCpv79MRuW/NofhvJbWaz6P8hY/au/OPwQDqz9/tIS/UGAZPpMGML+As2K+RKp2P3VFn732eQDA5rbBPgFQib8cp+c9iNe7v0SI9D4ovZy/aOcpvOS8R78Np3K+qpo4P/IBdT/5Zzo/YIiPPzRZZb1INUI/+Oo4PwvY+T3SVuY+UlVSP/OQQ758DNK/hz6Ev01wnj5ELPQ/Q0pWvivxTD/flWu+eYVePx2r1D5dlaY/3ZchPfCcuD4G9l6+TMrCPwU37ry8cVA/wr0zvqqaOD/yAXU/+Wc6P8RLZL+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLHIaUjAFDlHSUUpQu"
76
  },
77
  "_last_episode_starts": {
78
  ":type:": "<class 'numpy.ndarray'>",
 
80
  },
81
  "_last_original_obs": {
82
  ":type:": "<class 'numpy.ndarray'>",
83
+ ":serialized:": "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"
84
  },
85
  "_episode_num": 0,
86
  "use_sde": true,
 
88
  "_current_progress_remaining": -0.1200000000000001,
89
  "ep_info_buffer": {
90
  ":type:": "<class 'collections.deque'>",
91
+ ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
92
  },
93
  "ep_success_buffer": {
94
  ":type:": "<class 'collections.deque'>",
a2c-AntBulletEnv-v0/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20dcbae968712dc6e24294ade470dec9d840e44339764e942a67fec3809fd516
3
- size 55998
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ee66febc94a8ec689d14258ae684b21855ee351922fec3367834632a3455b51
3
+ size 56126
a2c-AntBulletEnv-v0/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da61658823e0240be381cff68065b2da97671c8747e9f731fe75477d4d6bd817
3
- size 56638
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8239193c6dd3e0b46a140ee94bdcc05d88b9e2ff83160feea3630f29241efb22
3
+ size 56766
a2c-AntBulletEnv-v0/system_info.txt CHANGED
@@ -1,7 +1,7 @@
1
- OS: Darwin-19.6.0-x86_64-i386-64bit Darwin Kernel Version 19.6.0: Tue Feb 15 21:39:11 PST 2022; root:xnu-6153.141.59~1/RELEASE_X86_64
2
- Python: 3.7.6
3
  Stable-Baselines3: 1.6.0
4
- PyTorch: 1.11.0
5
- GPU Enabled: False
6
- Numpy: 1.21.5
7
  Gym: 0.21.0
 
1
+ OS: Linux-5.4.0-122-generic-x86_64-with-glibc2.27 #138~18.04.1-Ubuntu SMP Fri Jun 24 14:14:03 UTC 2022
2
+ Python: 3.9.12
3
  Stable-Baselines3: 1.6.0
4
+ PyTorch: 1.12.0+cu102
5
+ GPU Enabled: True
6
+ Numpy: 1.23.1
7
  Gym: 0.21.0
config.json CHANGED
@@ -1 +1 @@
1
- {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__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 ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7fee25290830>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fee252908c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fee25290950>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fee252909e0>", "_build": "<function ActorCriticPolicy._build at 0x7fee25290a70>", "forward": "<function ActorCriticPolicy.forward at 0x7fee25290b00>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fee25290b90>", "_predict": "<function ActorCriticPolicy._predict at 0x7fee25290c20>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fee25290cb0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fee25290d40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fee25290dd0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fee2525ab40>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu", "log_std_init": -2, "ortho_init": false, "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [28], "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]", "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]", "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]", "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]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]", "high": "[1. 1. 1. 1. 1. 1. 1. 1.]", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_np_random": null}, "n_envs": 4, "num_timesteps": 224, "_total_timesteps": 200, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1659060932.07266, "learning_rate": 0.00096, "tensorboard_log": "./tensorboard", "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVBwMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxsL1VzZXJzL2ppYW56aGVuZ25pZS9vcHQvYW5hY29uZGEzL2VudnMvcHl0b3JjaC9saWIvcHl0aG9uMy43L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxsL1VzZXJzL2ppYW56aGVuZ25pZS9vcHQvYW5hY29uZGEzL2VudnMvcHl0b3JjaC9saWIvcHl0aG9uMy43L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz9PdRBNVR1phZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_episode_num": 0, "use_sde": true, "sde_sample_freq": -1, "_current_progress_remaining": -0.1200000000000001, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVZAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQB3yV8kUsWiMAWyUSxSMAXSURz/R5rxiG34LdX2UKGgGR0A4pthd+ocaaAdLLWgIRz/ZQuVX3g1ndWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 7, "n_steps": 8, "gamma": 0.99, "gae_lambda": 0.9, "ent_coef": 0.0, "vf_coef": 0.4, "max_grad_norm": 0.5, "normalize_advantage": false, "system_info": {"OS": "Darwin-19.6.0-x86_64-i386-64bit Darwin Kernel Version 19.6.0: Tue Feb 15 21:39:11 PST 2022; root:xnu-6153.141.59~1/RELEASE_X86_64", "Python": "3.7.6", "Stable-Baselines3": "1.6.0", "PyTorch": "1.11.0", "GPU Enabled": "False", "Numpy": "1.21.5", "Gym": "0.21.0"}}
 
1
+ {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__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 ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f40275aedc0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f40275aee50>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f40275aeee0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f40275aef70>", "_build": "<function ActorCriticPolicy._build at 0x7f40275b2040>", "forward": "<function ActorCriticPolicy.forward at 0x7f40275b20d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f40275b2160>", "_predict": "<function ActorCriticPolicy._predict at 0x7f40275b21f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f40275b2280>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f40275b2310>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f40275b23a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f40276a8d00>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu", "log_std_init": -2, "ortho_init": false, "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [28], "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]", "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]", "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]", "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]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]", "high": "[1. 1. 1. 1. 1. 1. 1. 1.]", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_np_random": null}, "n_envs": 4, "num_timesteps": 224, "_total_timesteps": 200, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1659066388.5388026, "learning_rate": 0.00096, "tensorboard_log": "work_dirs/AntBulletEnv-v0/tensorboard", "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_episode_num": 0, "use_sde": true, "sde_sample_freq": -1, "_current_progress_remaining": -0.1200000000000001, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 7, "n_steps": 8, "gamma": 0.99, "gae_lambda": 0.9, "ent_coef": 0.0, "vf_coef": 0.4, "max_grad_norm": 0.5, "normalize_advantage": false, "system_info": {"OS": "Linux-5.4.0-122-generic-x86_64-with-glibc2.27 #138~18.04.1-Ubuntu SMP Fri Jun 24 14:14:03 UTC 2022", "Python": "3.9.12", "Stable-Baselines3": "1.6.0", "PyTorch": "1.12.0+cu102", "GPU Enabled": "True", "Numpy": "1.23.1", "Gym": "0.21.0"}}
logs/a2c-AntBulletEnv-v0.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:772228a9a4d9e086c1e92c5b33d520c8f12a6f2ac23b79e45a4477fa5d2980d9
3
+ size 124978
logs/tensorboard/A2C_1/events.out.tfevents.1659066037.rlcube.25123.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dec255b825a6e666dbcd652a3e005c32602456b711dd34780d7df6ecb7a1999
3
+ size 40
logs/tensorboard/A2C_2/events.out.tfevents.1659066077.rlcube.25589.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e06a12d601f549e39ec8a90e6ec6592e6caeea7bd15801e4841869617bbca02e
3
+ size 40
logs/tensorboard/A2C_3/events.out.tfevents.1659066147.rlcube.26627.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23649725e85f73a8ec7a259a088dbd0a86e75cdaa9dd5d6b0ba2eb0dc4702bf8
3
+ size 40
logs/tensorboard/A2C_4/events.out.tfevents.1659066270.rlcube.27292.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6598d93f4b24ed4c50499d75720e39628039fc18afa0094d57c85ea80a91778
3
+ size 40
logs/tensorboard/A2C_5/events.out.tfevents.1659066388.rlcube.27802.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d20e58983c2ede83ffe88da62e07c6053b3046788064e9ae8f74ed96aadb10b
3
+ size 40
logs/vec_normalize.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0b392508ce6c26f1cec6f21bc88fbf848e85a948614f37206e4a8a3f7f6ba80
3
+ size 2453
replay.mp4 ADDED
Binary file (236 kB). View file
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 233.3024806248024, "std_reward": 154.47920955008576, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-29T10:16:01.592776"}
 
1
+ {"mean_reward": 319.91129219942377, "std_reward": 45.37349312855758, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-29T11:46:52.525094"}
vec_normalize.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c3d293736bc031fe86943da44f91bec71cd88ea182c70517e197caaa1b08641
3
- size 2763
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d605634e782a19c6dc2ba98a0b93622262ea131a9e45f102715f5f9fc5a1f358
3
+ size 2521