Push Reinforce agent to the Hub

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- CartPole-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: A2C
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 490.80 +/- 27.60
+      name: mean_reward
+      verified: false
+---
+
+# **A2C** Agent playing **CartPole-v1**
+This is a trained model of a **A2C** agent playing **CartPole-v1**
+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-cartpole-model.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:383ac32b10771999a5195897cabd7f893bc55fdffc879dfd9548bf8ac9d95055
+size 93368

a2c-cartpole-model/_stable_baselines3_version

@@ -0,0 +1 @@
+1.7.0

a2c-cartpole-model/data

@@ -0,0 +1,96 @@
+{
+    "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 0x000001D1C81AA3A0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001D1C81AA430>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001D1C81AA4C0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001D1C81AA550>",
+        "_build": "<function ActorCriticPolicy._build at 0x000001D1C81AA5E0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x000001D1C81AA670>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x000001D1C81AA700>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001D1C81AA790>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x000001D1C81AA820>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001D1C81AA8B0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001D1C81AA940>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001D1C81AA9D0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x000001D1C7D4B080>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=",
+        "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": [
+            4
+        ],
+        "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
+        "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
+        "bounded_below": "[ True  True  True  True]",
+        "bounded_above": "[ True  True  True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLAowGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 2,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 1,
+    "num_timesteps": 10000,
+    "_total_timesteps": 10000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1676327705715988700,
+    "learning_rate": 0.0007,
+    "tensorboard_log": "runs/5rq01s5y",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAC7C674nVy0+D+w9vlCCn7yUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "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": 2000,
+    "n_steps": 5,
+    "gamma": 0.99,
+    "gae_lambda": 1.0,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "normalize_advantage": false
+}

a2c-cartpole-model/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f816c727538fccf29f8f75b5721ab032a9a1a5bb0dfdb966c8abc908ee4fc2ad
+size 39937

a2c-cartpole-model/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f8c9e125812c7e597bac03248e69d96fc5c28cc0385991d060cd87e3896a5af
+size 40705

a2c-cartpole-model/pytorch_variables.pth

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

a2c-cartpole-model/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Windows-10-10.0.22000-SP0 10.0.22000
+- Python: 3.9.0
+- Stable-Baselines3: 1.7.0
+- PyTorch: 1.13.0+cpu
+- GPU Enabled: False
+- Numpy: 1.23.3
+- 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 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 0x000001D1C81AA3A0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001D1C81AA430>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001D1C81AA4C0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001D1C81AA550>", "_build": "<function ActorCriticPolicy._build at 0x000001D1C81AA5E0>", "forward": "<function ActorCriticPolicy.forward at 0x000001D1C81AA670>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x000001D1C81AA700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001D1C81AA790>", "_predict": "<function ActorCriticPolicy._predict at 0x000001D1C81AA820>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001D1C81AA8B0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001D1C81AA940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001D1C81AA9D0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000001D1C7D4B080>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "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": [4], "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "bounded_below": "[ True  True  True  True]", "bounded_above": "[ True  True  True  True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLAowGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 2, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 10000, "_total_timesteps": 10000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1676327705715988700, "learning_rate": 0.0007, "tensorboard_log": "runs/5rq01s5y", "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAC7C674nVy0+D+w9vlCCn7yUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "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": 2000, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "normalize_advantage": false, "system_info": {"OS": "Windows-10-10.0.22000-SP0 10.0.22000", "Python": "3.9.0", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.0+cpu", "GPU Enabled": "False", "Numpy": "1.23.3", "Gym": "0.21.0"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": 490.8, "std_reward": 27.6, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-13T23:35:44.578681"}