Test commit

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: 500.00 +/- 0.00
+      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.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb05816cb2803245361049807d39abc0ca0eb0104aa8803965fb1ad53721d47e
+size 94182

a2c_cartpole/_stable_baselines3_version

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

a2c_cartpole/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 0x7f64416ceb00>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f64416ceb90>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f64416cec20>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f64416cecb0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f64416ced40>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f64416cedd0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f64416cee60>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f64416ceef0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f64416cef80>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f64416cf010>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f64416cf0a0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f64416cf130>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f64416ca500>"
+    },
+    "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:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLAowGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 2,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 4,
+    "num_timesteps": 100000,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1675700934397046081,
+    "learning_rate": 0.0007,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVtQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZAAAAAAAAAABsCkLz/dFC+gYNUO0ZagT5r27I/jTo+Pvy1KLzPkMu906pbPlPJ4rxz+Ce910DMPsWhoj9qEJ884ZXcuiFyGz6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLBIaUjAFDlHSUUpQu"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
+    },
+    "_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": 5000,
+    "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/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42276e11adf607d1c1f240e2b3b445cafc987f85758e1d107395f95156643991
+size 40065

a2c_cartpole/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0237e1843ddbaf361eca61b87c93d91f44553805fcb05a5b6df6252a66e5fde8
+size 40833

a2c_cartpole/pytorch_variables.pth

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

a2c_cartpole/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.15.0-58-generic-x86_64-with-glibc2.35 # 64-Ubuntu SMP Thu Jan 5 11:43:13 UTC 2023
+- Python: 3.10.6
+- Stable-Baselines3: 1.7.0
+- PyTorch: 1.13.1+cu117
+- GPU Enabled: True
+- Numpy: 1.24.2
+- 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 0x7f64416ceb00>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f64416ceb90>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f64416cec20>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f64416cecb0>", "_build": "<function ActorCriticPolicy._build at 0x7f64416ced40>", "forward": "<function ActorCriticPolicy.forward at 0x7f64416cedd0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f64416cee60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f64416ceef0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f64416cef80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f64416cf010>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f64416cf0a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f64416cf130>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f64416ca500>"}, "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:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLAowGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 2, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 4, "num_timesteps": 100000, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1675700934397046081, "learning_rate": 0.0007, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVtQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZAAAAAAAAAABsCkLz/dFC+gYNUO0ZagT5r27I/jTo+Pvy1KLzPkMu906pbPlPJ4rxz+Ce910DMPsWhoj9qEJ884ZXcuiFyGz6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLBIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_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": 5000, "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": "Linux-5.15.0-58-generic-x86_64-with-glibc2.35 # 64-Ubuntu SMP Thu Jan 5 11:43:13 UTC 2023", "Python": "3.10.6", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.2", "Gym": "0.21.0"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-06T17:29:33.642092"}