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: 434.14 +/- 66.87
+      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:b5538ec0e7021009d23166b0df931bab24eebda16739113b392c80f0883e6ba1
+size 125261

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:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
+        "__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 0x7f6454f2def0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6454f2df80>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6454f31050>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6454f310e0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f6454f31170>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f6454f31200>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6454f31290>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f6454f31320>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6454f313b0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6454f31440>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6454f314d0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f6454f81780>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gASVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/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": 1024,
+    "_total_timesteps": 1000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1658738092.0043716,
+    "learning_rate": 0.00096,
+    "tensorboard_log": "./tensorboard",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVTQIAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwRLHIaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiULAAQAAqodCPyZ4MD8tsjE/pMMmPlpqaT/IObk+9RQXv68FlT++uIg/R5kmv67S7LyF1f0+DEM5Pz+PlT2DNs6/kutnPl5Bzj1wuBA/dzv1PoJkHT5t2U6/0cCRv7WkpT8jHgy/W8cyPx3yPT8/Z5+/WME0Pzf5hr9B3fi+0mzVPvoWbj3ENUW/0SyePmk6Pb/S3s2+vZaLv64jer7d4wO/n9tjvo+XND475g2/LwZuP1vChz7gADy/6PIRv0L49j5qmU4+jpCDv8serz0oRne+DO4NvlvHMj8d8j0/CZFNP6JItb/aVIU/3b7zvvNO2z7vATM+mvfLvgyAoj51dTA+mjetvimqrj8OlDa9JQzNP4FdSb8BI74+mTTfv7/UzL+rI4O9ObKsP8nsGb9H/4S/31IiwIp2az9BU4k/aLCdPxjtIL62Sbe/HfI9PwmRTT9YwTQ/b3bOPXm1xL/UWNq/lLYKPezTpj5eTQA/1xxhQEiuvb6qLq4/kanJOm9l2D9xIR2+JZi8PiViV7/P7Mi/jEyiPswUxb/59nQ9oUT3PmKgHz4iaLY/d1mOPUp7F77yto69tkm3vyiDrL8JkU0/WME0P5R0lGIu"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVjAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwSFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDBAAAAACUdJRiLg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVTQIAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwRLHIaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiULAAQAAAAAAAEpwjTYAAIA/AAAAAAAAAAAAAAAAAAAAAAAAAICMloC7AAAAAEme7r8AAAAAqM15vAAAAAARceo/AAAAADngoz0AAAAAmp3lPwAAAADtMfa9AAAAAHGU6L8AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAD2pFw2AACAPwAAAAAAAAAAAAAAAAAAAAAAAACAfUwCvgAAAABwxOS/AAAAAKARoD0AAAAAmE/iPwAAAACLpOW9AAAAAG8aAEAAAAAAdTs+vQAAAABXYeS/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABb5EtwAAgD8AAAAAAAAAAAAAAAAAAAAAAAAAgJrp0D0AAAAAOpfhvwAAAACWfwq+AAAAAAce6T8AAAAAY7oKvgAAAACUGfY/AAAAAGcxBD4AAAAAT8z9vwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACPgKDYAAIA/AAAAAAAAAAAAAAAAAAAAAAAAAIDPf4s8AAAAAHCb+r8AAAAARNLsuwAAAADNitk/AAAAAJZr3j0AAAAAvH/ZPwAAAAAjpPK8AAAAAM5KAcAAAAAAAAAAAAAAAAAAAAAAAAAAAJR0lGIu"
+    },
+    "_episode_num": 0,
+    "use_sde": true,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.02400000000000002,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVvgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQBrCYkVvddqMAWyUSxSMAXSUR0B7RiC04R29dX2UKGgGR0AYbvb48EFGaAdLFGgIR0B7RiJtSAH3dX2UKGgGR0AykfigkC3gaAdLOGgIR0B7SaraM72ddX2UKGgGR0BUTIoZydWiaAdLiWgIR0B7U46Lfk3kdX2UKGgGR0BRBqiCaqjraAdLuWgIR0B7VkmReTmodWUu"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 32,
+    "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:a01f6e19c96e995a9bf2306a0fb51b1085f35a2e59a2d35dbec1291f13a4bfc6
+size 56126

a2c-AntBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8462bcb302d11f1207b3b430c65f8e51b1370f255754ff1bbdc0ae1d1a4f33dd
+size 56766

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: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
+Python: 3.7.13
+Stable-Baselines3: 1.6.0
+PyTorch: 1.12.0+cu113
+GPU Enabled: True
+Numpy: 1.21.6
+Gym: 0.21.0

config.json

@@ -0,0 +1 @@
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7f6454f2def0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6454f2df80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6454f31050>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6454f310e0>", "_build": "<function ActorCriticPolicy._build at 0x7f6454f31170>", "forward": "<function ActorCriticPolicy.forward at 0x7f6454f31200>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6454f31290>", "_predict": "<function ActorCriticPolicy._predict at 0x7f6454f31320>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6454f313b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6454f31440>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6454f314d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f6454f81780>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gASVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/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": 1024, "_total_timesteps": 1000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1658738092.0043716, "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:": "gASVjAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwSFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDBAAAAACUdJRiLg=="}, "_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": -0.02400000000000002, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVvgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQBrCYkVvddqMAWyUSxSMAXSUR0B7RiC04R29dX2UKGgGR0AYbvb48EFGaAdLFGgIR0B7RiJtSAH3dX2UKGgGR0AykfigkC3gaAdLOGgIR0B7SaraM72ddX2UKGgGR0BUTIoZydWiaAdLiWgIR0B7U46Lfk3kdX2UKGgGR0BRBqiCaqjraAdLuWgIR0B7VkmReTmodWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 32, "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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.6.0", "PyTorch": "1.12.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": 434.13707664154936, "std_reward": 66.87121672129756, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-25T08:37:53.424223"}

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef5ffa03565f2440db5583ad54387900ce5f91ec5f4259cf2b8afea106b64f10
+size 2763