Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: AntBulletEnv-v0
     metrics:
     - type: mean_reward
-      value: 1542.37 +/- 101.27
+      value: 1591.41 +/- 104.62
       name: mean_reward
       verified: false
 ---

a2c-AntBulletEnv-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b1d8fab0b40fcffe8f084607008a9251e74f659c4871d002b0372435a2c791d
+oid sha256:44e57c04df9991da809b1aff087835e105d22bb6400eaa781237632b392fa336
 size 129324

a2c-AntBulletEnv-v0/data

@@ -4,20 +4,20 @@
         ":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 0x7fc497500dc0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc497500e50>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc497500ee0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc497500f70>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fc497501000>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fc497501090>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc497501120>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc4975011b0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fc497501240>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc4975012d0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc497501360>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc4975013f0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f0dfa4492d0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0dfa449360>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0dfa4493f0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0dfa449480>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f0dfa449510>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f0dfa4495a0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f0dfa449630>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0dfa4496c0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f0dfa449750>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0dfa4497e0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0dfa449870>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0dfa449900>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fc4974fcfc0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f0dfadc9740>"
     },
     "verbose": 1,
     "policy_kwargs": {

config.json

@@ -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 0x7fc497500dc0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc497500e50>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc497500ee0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc497500f70>", "_build": "<function ActorCriticPolicy._build at 0x7fc497501000>", "forward": "<function ActorCriticPolicy.forward at 0x7fc497501090>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc497501120>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc4975011b0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc497501240>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc4975012d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc497501360>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc4975013f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fc4974fcfc0>"}, "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}}, "num_timesteps": 2000000, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1684264126584454730, "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:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": 0.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 62500, "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, "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, "system_info": {"OS": "Linux-5.15.0-69-generic-x86_64-with-glibc2.31 # 76~20.04.1-Ubuntu SMP Mon Mar 20 15:54:19 UTC 2023", "Python": "3.10.11", "Stable-Baselines3": "1.8.0", "PyTorch": "2.0.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.3", "Gym": "0.21.0"}}
+{"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 0x7f0dfa4492d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f0dfa449360>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f0dfa4493f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f0dfa449480>", "_build": "<function ActorCriticPolicy._build at 0x7f0dfa449510>", "forward": "<function ActorCriticPolicy.forward at 0x7f0dfa4495a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f0dfa449630>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f0dfa4496c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f0dfa449750>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f0dfa4497e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f0dfa449870>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f0dfa449900>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f0dfadc9740>"}, "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}}, "num_timesteps": 2000000, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1684264126584454730, "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:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": 0.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 62500, "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, "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, "system_info": {"OS": "Linux-5.15.0-69-generic-x86_64-with-glibc2.31 # 76~20.04.1-Ubuntu SMP Mon Mar 20 15:54:19 UTC 2023", "Python": "3.10.11", "Stable-Baselines3": "1.8.0", "PyTorch": "2.0.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.3", "Gym": "0.21.0"}}

results.json

@@ -1 +1 @@
-{"mean_reward": 1542.3741817889108, "std_reward": 101.27080628464701, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-16T17:05:05.685385"}
+{"mean_reward": 1591.4103807194856, "std_reward": 104.62365974523692, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-17T14:24:35.873134"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7f1ce18d8af2b691ffca5f0ec8536ebb699295d28233596a20ab736b59a61aa
-size 2493
+oid sha256:bee29872ec951c1f63af6c0c01a8569f4231e1c8a5bfece4180c71485ba5d13c
+size 2176