initial implementation

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLander-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 259.79 +/- 14.17
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **LunarLander-v2**
+This is a trained model of a **PPO** agent playing **LunarLander-v2**
+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 0x7e529ba0d120>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e529ba0d1b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e529ba0d240>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e529ba0d2d0>", "_build": "<function ActorCriticPolicy._build at 0x7e529ba0d360>", "forward": "<function ActorCriticPolicy.forward at 0x7e529ba0d3f0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e529ba0d480>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e529ba0d510>", "_predict": "<function ActorCriticPolicy._predict at 0x7e529ba0d5a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e529ba0d630>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e529ba0d6c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e529ba0d750>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e529b9aa880>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1711130408364151942, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_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": -0.015808000000000044, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27248e1a951017519299f1c5fbe06d1ab80c572798721325f5245e6c942e958d
+size 147312

ppo-LunarLander-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a5

ppo-LunarLander-v2/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 0x7e529ba0d120>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e529ba0d1b0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e529ba0d240>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e529ba0d2d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7e529ba0d360>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7e529ba0d3f0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e529ba0d480>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e529ba0d510>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7e529ba0d5a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e529ba0d630>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e529ba0d6c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e529ba0d750>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7e529b9aa880>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1711130408364151942,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_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": -0.015808000000000044,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 248,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True]",
+        "_shape": [
+            8
+        ],
+        "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
+        "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
+        "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
+        "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 1,
+    "n_steps": 1024,
+    "gamma": 0.999,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 4,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

ppo-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:090ab08f82680a3e7295b068577d275ecb8e5a897eb6ca2e30f901e8477a5987
+size 88490

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f47e9b062bfc29c8dde531232fdcfad7822bbe84d69bff429d7314c24ed6bc
+size 43762

ppo-LunarLander-v2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

ppo-LunarLander-v2/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.2.1+cu121
+- GPU Enabled: True
+- Numpy: 1.25.2
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": 259.7912844, "std_reward": 14.174904214788757, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-22T18:26:36.945675"}