Initial commit

.gitattributes

@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,28 @@
+---
+library_name: stable-baselines3
+tags:
+- HalfCheetahBulletEnv-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: A2C
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 1498.70 +/- 811.27
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: HalfCheetahBulletEnv-v0
+      type: HalfCheetahBulletEnv-v0
+---
+
+  # **A2C** Agent playing **HalfCheetahBulletEnv-v0**
+  This is a trained model of a **A2C** agent playing **HalfCheetahBulletEnv-v0** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+  
+  ## Usage (with Stable-baselines3)
+  TODO: Add your code
+  

a2c-HalfCheetahBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b3cf6e1bee8759d3aa5ce12e03a9310d673d2f34074d3ae0eefc47e0d300ab
+size 121752

a2c-HalfCheetahBulletEnv-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.0

a2c-HalfCheetahBulletEnv-v0/data

@@ -0,0 +1,105 @@
+{
+    "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 0x7f29c7aff3a0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f29c7aff430>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f29c7aff4c0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f29c7aff550>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f29c7aff5e0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f29c7aff670>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f29c7aff700>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f29c7aff790>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f29c7aff820>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f29c7aff8b0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f29c7aff940>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f29c7cc8e00>"
+    },
+    "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": [
+            26
+        ],
+        "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]",
+        "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]",
+        "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]",
+        "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]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            6
+        ],
+        "low": "[-1. -1. -1. -1. -1. -1.]",
+        "high": "[1. 1. 1. 1. 1. 1.]",
+        "bounded_below": "[ True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True]",
+        "_np_random": null
+    },
+    "n_envs": 8,
+    "num_timesteps": 0,
+    "_total_timesteps": 2000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1659352750.6474247,
+    "learning_rate": 0.00096,
+    "tensorboard_log": "./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:": "gAWVewAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAEBAQEBAQEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlC4="
+    },
+    "_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,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 156250,
+    "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
+}

a2c-HalfCheetahBulletEnv-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881db562d557671f8ffab3f407b366985fab53b319ab8a86670c9fe51101be5e
+size 54142

a2c-HalfCheetahBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81a732e964155b759d816eb58cf0534ed628c9f523ddcf17c76c11aa24012bb1
+size 54718

a2c-HalfCheetahBulletEnv-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

a2c-HalfCheetahBulletEnv-v0/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.11.0-38-generic-x86_64-with-glibc2.31 #42~20.04.1-Ubuntu SMP Tue Sep 28 20:41:07 UTC 2021
+Python: 3.9.12
+Stable-Baselines3: 1.5.0
+PyTorch: 1.11.0+cu102
+GPU Enabled: True
+Numpy: 1.22.3
+Gym: 0.21.0

config.json

@@ -0,0 +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 0x7f29c7aff3a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f29c7aff430>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f29c7aff4c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f29c7aff550>", "_build": "<function ActorCriticPolicy._build at 0x7f29c7aff5e0>", "forward": "<function ActorCriticPolicy.forward at 0x7f29c7aff670>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f29c7aff700>", "_predict": "<function ActorCriticPolicy._predict at 0x7f29c7aff790>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f29c7aff820>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f29c7aff8b0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f29c7aff940>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f29c7cc8e00>"}, "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": [26], "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]", "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]", "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]", "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]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [6], "low": "[-1. -1. -1. -1. -1. -1.]", "high": "[1. 1. 1. 1. 1. 1.]", "bounded_below": "[ True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True]", "_np_random": null}, "n_envs": 8, "num_timesteps": 0, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1659352750.6474247, "learning_rate": 0.00096, "tensorboard_log": "./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:": "gAWVewAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAEBAQEBAQEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlC4="}, "_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, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 156250, "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-5.11.0-38-generic-x86_64-with-glibc2.31 #42~20.04.1-Ubuntu SMP Tue Sep 28 20:41:07 UTC 2021", "Python": "3.9.12", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu102", "GPU Enabled": "True", "Numpy": "1.22.3", "Gym": "0.21.0"}}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2039d93a92960e1736026fd44316515c265b3a380dd66a279e3e3d3f578068e9
+size 1213533

results.json

@@ -0,0 +1 @@
+{"mean_reward": 1498.700125034753, "std_reward": 811.270000971616, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-01T13:19:53.773557"}