Upload PPO FrozenLake agent trained for 1M steps with default hyperparameters

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: 0.70 +/- 0.46
+      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 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 0x16482f820>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x16482f8b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x16482f940>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x16482f9d0>", "_build": "<function ActorCriticPolicy._build at 0x16482fa60>", "forward": "<function ActorCriticPolicy.forward at 0x16482faf0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x16482fb80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x16482fc10>", "_predict": "<function ActorCriticPolicy._predict at 0x16482fca0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x16482fd30>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x16482fdc0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x16482fe50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x1648314c0>"}, "verbose": 0, "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": 1, "num_timesteps": 1001472, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1677532986508488000, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVewAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="}, "_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": -0.0014719999999999178, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 4890, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "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": "macOS-13.2.1-arm64-arm-64bit Darwin Kernel Version 22.3.0: Mon Jan 30 20:39:35 PST 2023; root:xnu-8792.81.3~2/RELEASE_ARM64_T8103", "Python": "3.9.7", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1", "GPU Enabled": "False", "Numpy": "1.23.5", "Gym": "0.21.0"}}

ppo-FrozenLake-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0db8fe2c777f589e59e215914ee021f3801d4c32a15129da9bccb7985ab9f2e2
+size 156484

ppo-FrozenLake-v1/_stable_baselines3_version

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

ppo-FrozenLake-v1/data

@@ -0,0 +1,90 @@
+{
+    "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 0x16482f820>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x16482f8b0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x16482f940>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x16482f9d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x16482fa60>",
+        "forward": "<function ActorCriticPolicy.forward at 0x16482faf0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x16482fb80>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x16482fc10>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x16482fca0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x16482fd30>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x16482fdc0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x16482fe50>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x1648314c0>"
+    },
+    "verbose": 0,
+    "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": 1,
+    "num_timesteps": 1001472,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1677532986508488000,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVewAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="
+    },
+    "_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": -0.0014719999999999178,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 4890,
+    "n_steps": 2048,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 10,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-FrozenLake-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5881bc2f96cf63055073bb716552dc52dca4ab591c6da93a8c807f850b19c27a
+size 95737

ppo-FrozenLake-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1734ce7084ea9cd97dce4faaee21f45bb7828e5cbfc4d6c7cb74e16376223f80
+size 47361

ppo-FrozenLake-v1/pytorch_variables.pth

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

ppo-FrozenLake-v1/system_info.txt

@@ -0,0 +1,7 @@
+- OS: macOS-13.2.1-arm64-arm-64bit Darwin Kernel Version 22.3.0: Mon Jan 30 20:39:35 PST 2023; root:xnu-8792.81.3~2/RELEASE_ARM64_T8103
+- Python: 3.9.7
+- Stable-Baselines3: 1.7.0
+- PyTorch: 1.13.1
+- GPU Enabled: False
+- Numpy: 1.23.5
+- Gym: 0.21.0

results.json

@@ -0,0 +1 @@
+{"mean_reward": 0.7, "std_reward": 0.45825756949558394, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T22:28:58.490013"}