feat: PPO creation for lunar lander env

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: 280.46 +/- 17.47
+      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 0x78ae31a56440>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78ae31a564d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78ae31a56560>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78ae31a565f0>", "_build": "<function ActorCriticPolicy._build at 0x78ae31a56680>", "forward": "<function ActorCriticPolicy.forward at 0x78ae31a56710>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x78ae31a567a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78ae31a56830>", "_predict": "<function ActorCriticPolicy._predict at 0x78ae31a568c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78ae31a56950>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78ae31a569e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x78ae31a56a70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78ae31a51840>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1710517840299609891, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_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": -0.007616000000000067, "_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": 548, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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 sha256:5b4266ac0d3f39243bd3c35cb8abc2f6c0aa604b3eb4a096f314d75460cd963c
+size 147988

ppo-LunarLander-v2/_stable_baselines3_version

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

ppo-LunarLander-v2/data

@@ -0,0 +1,99 @@
+{
+    "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 0x78ae31a56440>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78ae31a564d0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78ae31a56560>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78ae31a565f0>",
+        "_build": "<function ActorCriticPolicy._build at 0x78ae31a56680>",
+        "forward": "<function ActorCriticPolicy.forward at 0x78ae31a56710>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x78ae31a567a0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78ae31a56830>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x78ae31a568c0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78ae31a56950>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78ae31a569e0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x78ae31a56a70>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x78ae31a51840>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 2015232,
+    "_total_timesteps": 2000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1710517840299609891,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_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": -0.007616000000000067,
+    "_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": 548,
+    "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "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 sha256:95db14484484423d19f417f873ef2414a89a34f2770c53f6d56a0e1cbd7c75dd
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf0c349a09fb0125fea7224f8562ad249cf510f7520a8f4496e677e0f1f06c9
+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": 280.4611251, "std_reward": 17.47012177471855, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-15T16:26:28.256935"}