Initial commit

README.md

@@ -0,0 +1,36 @@
+---
+library_name: stable-baselines3
+tags:
+- AntBulletEnv-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: A2C
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 233.30 +/- 154.48
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: AntBulletEnv-v0
+      type: AntBulletEnv-v0
+---
+
+# **A2C** Agent playing **AntBulletEnv-v0**
+This is a trained model of a **A2C** agent playing **AntBulletEnv-v0**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+
+## Usage (with Stable-baselines3)
+TODO: Add your code
+
+
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+
+...
+```

a2c-AntBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f2306c3827c88bf725aabac539694f0d98982cbb20f9159cbda1f09bcc6dddb
+size 124828

a2c-AntBulletEnv-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.6.0

a2c-AntBulletEnv-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 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:": "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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:": "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
+}

a2c-AntBulletEnv-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20dcbae968712dc6e24294ade470dec9d840e44339764e942a67fec3809fd516
+size 55998

a2c-AntBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da61658823e0240be381cff68065b2da97671c8747e9f731fe75477d4d6bd817
+size 56638

a2c-AntBulletEnv-v0/pytorch_variables.pth

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

a2c-AntBulletEnv-v0/system_info.txt

@@ -0,0 +1,7 @@
+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

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 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:": "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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:": "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"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": 233.3024806248024, "std_reward": 154.47920955008576, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-29T10:16:01.592776"}

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c3d293736bc031fe86943da44f91bec71cd88ea182c70517e197caaa1b08641
+size 2763