Initial commit
Browse files- README.md +1 -1
- a2c-AntBulletEnv-v0.zip +2 -2
- a2c-AntBulletEnv-v0/data +23 -38
- a2c-AntBulletEnv-v0/policy.optimizer.pth +2 -2
- a2c-AntBulletEnv-v0/policy.pth +1 -1
- config.json +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
- vec_normalize.pkl +2 -2
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: AntBulletEnv-v0
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: AntBulletEnv-v0
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 325.22 +/- 220.83
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
a2c-AntBulletEnv-v0.zip
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 sha256:37eb2236c322428302dc0338f12ef24a2f6e77ce1051892e05dea7a0f19230fc
|
3 |
+
size 67370
|
a2c-AntBulletEnv-v0/data
CHANGED
@@ -4,20 +4,20 @@
|
|
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc._abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {
|
@@ -59,43 +59,28 @@
|
|
59 |
"_np_random": null
|
60 |
},
|
61 |
"n_envs": 4,
|
62 |
-
"num_timesteps":
|
63 |
-
"_total_timesteps":
|
64 |
"_num_timesteps_at_start": 0,
|
65 |
"seed": null,
|
66 |
"action_noise": null,
|
67 |
-
"start_time":
|
68 |
"learning_rate": 0.00096,
|
69 |
"tensorboard_log": null,
|
70 |
"lr_schedule": {
|
71 |
":type:": "<class 'function'>",
|
72 |
":serialized:": "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"
|
73 |
},
|
74 |
-
"_last_obs":
|
75 |
-
|
76 |
-
|
77 |
-
},
|
78 |
-
"_last_episode_starts": {
|
79 |
-
":type:": "<class 'numpy.ndarray'>",
|
80 |
-
":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
|
81 |
-
},
|
82 |
-
"_last_original_obs": {
|
83 |
-
":type:": "<class 'numpy.ndarray'>",
|
84 |
-
":serialized:": "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"
|
85 |
-
},
|
86 |
"_episode_num": 0,
|
87 |
"use_sde": true,
|
88 |
"sde_sample_freq": -1,
|
89 |
-
"_current_progress_remaining":
|
90 |
-
"ep_info_buffer":
|
91 |
-
|
92 |
-
|
93 |
-
},
|
94 |
-
"ep_success_buffer": {
|
95 |
-
":type:": "<class 'collections.deque'>",
|
96 |
-
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
97 |
-
},
|
98 |
-
"_n_updates": 93750,
|
99 |
"n_steps": 8,
|
100 |
"gamma": 0.99,
|
101 |
"gae_lambda": 0.9,
|
|
|
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7f38f101af70>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f38f1020040>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f38f10200d0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f38f1020160>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f38f10201f0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f38f1020280>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f38f1020310>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f38f10203a0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f38f1020430>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f38f10204c0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f38f1020550>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f38f10205e0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f38f1021240>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {
|
|
|
59 |
"_np_random": null
|
60 |
},
|
61 |
"n_envs": 4,
|
62 |
+
"num_timesteps": 0,
|
63 |
+
"_total_timesteps": 0,
|
64 |
"_num_timesteps_at_start": 0,
|
65 |
"seed": null,
|
66 |
"action_noise": null,
|
67 |
+
"start_time": null,
|
68 |
"learning_rate": 0.00096,
|
69 |
"tensorboard_log": null,
|
70 |
"lr_schedule": {
|
71 |
":type:": "<class 'function'>",
|
72 |
":serialized:": "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"
|
73 |
},
|
74 |
+
"_last_obs": null,
|
75 |
+
"_last_episode_starts": null,
|
76 |
+
"_last_original_obs": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
77 |
"_episode_num": 0,
|
78 |
"use_sde": true,
|
79 |
"sde_sample_freq": -1,
|
80 |
+
"_current_progress_remaining": 1,
|
81 |
+
"ep_info_buffer": null,
|
82 |
+
"ep_success_buffer": null,
|
83 |
+
"_n_updates": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
84 |
"n_steps": 8,
|
85 |
"gamma": 0.99,
|
86 |
"gae_lambda": 0.9,
|
a2c-AntBulletEnv-v0/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:763e6aa37fb83f8a1ec0724e39a562418a7d4e18293f64bc65670e025bf41c6e
|
3 |
+
size 687
|
a2c-AntBulletEnv-v0/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 56958
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4071279cfa9bd4331a087e5f7a6661ac2b0086bd48e617a94b27f5ac653d117d
|
3 |
size 56958
|
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7f14722e2e50>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f14722e2ee0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f14722e2f70>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f14722e4040>", "_build": "<function ActorCriticPolicy._build at 0x7f14722e40d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f14722e4160>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f14722e41f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f14722e4280>", "_predict": "<function ActorCriticPolicy._predict at 0x7f14722e4310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f14722e43a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f14722e4430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f14722e44c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f14722e5200>"}, "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:": "gAWVZwIAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLHIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWcAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/lGgKSxyFlIwBQ5R0lFKUjARoaWdolGgSKJZwAAAAAAAAAAAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH+UaApLHIWUaBV0lFKUjA1ib3VuZGVkX2JlbG93lGgSKJYcAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLHIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYcAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUaCFLHIWUaBV0lFKUjApfbnBfcmFuZG9tlE51Yi4=", "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": 3000000, "_total_timesteps": 3000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1680081873856638933, "learning_rate": 0.00096, "tensorboard_log": null, "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:": "gAWVNQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJbAAQAAAAAAAAAAAABVZSI1AACAPwAAAAAAAAAAAAAAAAAAAAAAAACAdmqCOwAAAABLVOa/AAAAAIhiVTwAAAAAv53jPwAAAAAGKu49AAAAAFdM/z8AAAAAEse5PQAAAACvzOa/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAjEX2MwAAgD8AAAAAAAAAAAAAAAAAAAAAAAAAgOak0D0AAAAAkdn1vwAAAAAu6KW9AAAAAD1D8D8AAAAAM/mpPQAAAACrSOs/AAAAAELR2L0AAAAABNDfvwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAIQokLYAAIA/AAAAAAAAAAAAAAAAAAAAAAAAAIAvI2i8AAAAAK0k+b8AAAAAB57COwAAAAAlCgBAAAAAABDcor0AAAAAW6jqPwAAAADmHPM9AAAAAOZi2b8AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAC16E41AACAPwAAAAAAAAAAAAAAAAAAAAAAAACAVLkcvQAAAACpi+u/AAAAAILhXj0AAAAA/lH7PwAAAAAYegy+AAAAAE6S6j8AAAAAP8ysvQAAAABseee/AAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLHIaUjAFDlHSUUpQu"}, "_episode_num": 0, "use_sde": true, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 93750, "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-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7f38f101af70>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f38f1020040>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f38f10200d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f38f1020160>", "_build": "<function ActorCriticPolicy._build at 0x7f38f10201f0>", "forward": "<function ActorCriticPolicy.forward at 0x7f38f1020280>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f38f1020310>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f38f10203a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f38f1020430>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f38f10204c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f38f1020550>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f38f10205e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f38f1021240>"}, "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": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": null, "learning_rate": 0.00096, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": true, "sde_sample_freq": -1, "_current_progress_remaining": 1, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "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-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.9.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
|
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 sha256:27ff81216d78b179c57322c53f48601ede973d76458796fcdf242b0aee06cc20
|
3 |
+
size 374126
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 325.22054684609174, "std_reward": 220.82899618321915, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-29T12:06:52.089688"}
|
vec_normalize.pkl
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 sha256:0d96ba06e37511ea33a42feda7687377863601780b8c5072ac08e8cdd7b6e500
|
3 |
+
size 2123
|