upload agent

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- FrozenLake-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: FrozenLake-v1
+      type: FrozenLake-v1
+    metrics:
+    - type: mean_reward
+      value: 0.80 +/- 0.40
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **FrozenLake-v1**
+This is a trained model of a **PPO** agent playing **FrozenLake-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
+
+...
+```

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 0x7f7977995cb0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7977995d40>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7977995dd0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7977995e60>", "_build": "<function ActorCriticPolicy._build at 0x7f7977995ef0>", "forward": "<function ActorCriticPolicy.forward at 0x7f7977995f80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f797799c050>", "_predict": "<function ActorCriticPolicy._predict at 0x7f797799c0e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f797799c170>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f797799c200>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f797799c290>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f79779e96c0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLEIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 16, "_shape": [], "dtype": "int64", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 500096, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1666088247380034247, "learning_rate": 0.0001, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV8wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAAQAAAAAAAAACAAAAAAAAAAOAAAAAAAAAAgAAAAAAAAADgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACgAAAAAAAAAGAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00019199999999996997, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 39070, "n_steps": 8, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.133+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.7.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.1+cu113", "GPU Enabled": "False", "Numpy": "1.21.6", "Gym": "0.21.0"}}

ppo-MountainCar-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:443f42064d14e059f31b11f419435ccd72f54b01d7aa75f4759edf36c1a21760
+size 156253

ppo-MountainCar-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.6.2

ppo-MountainCar-v0/data

@@ -0,0 +1,89 @@
+{
+    "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 0x7f7977995cb0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7977995d40>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7977995dd0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7977995e60>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f7977995ef0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f7977995f80>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f797799c050>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f797799c0e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f797799c170>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f797799c200>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f797799c290>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f79779e96c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLEIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 16,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 4,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "num_timesteps": 500096,
+    "_total_timesteps": 500000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1666088247380034247,
+    "learning_rate": 0.0001,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV8wAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAAQAAAAAAAAACAAAAAAAAAAOAAAAAAAAAAgAAAAAAAAADgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACgAAAAAAAAAGAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAEAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.00019199999999996997,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 39070,
+    "n_steps": 8,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 128,
+    "n_epochs": 10,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-MountainCar-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d28236efecec165eb16a78c8e99fcfb7d2bb748fbc58a94a12d5ab8126d8181a
+size 95737

ppo-MountainCar-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b1f7bf3d4f1ba8800cebecd6a7baad4242d06f823ab7b9368f6c31de3743b94
+size 47169

ppo-MountainCar-v0/pytorch_variables.pth

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

ppo-MountainCar-v0/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.10.133+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Fri Aug 26 08:44:51 UTC 2022
+Python: 3.7.15
+Stable-Baselines3: 1.6.2
+PyTorch: 1.12.1+cu113
+GPU Enabled: False
+Numpy: 1.21.6
+Gym: 0.21.0

results.json

@@ -0,0 +1 @@
+{"mean_reward": 0.8, "std_reward": 0.4, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-10-18T10:22:28.900445"}