Upload PPO LunarLander-v2 trained agent

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: 283.54 +/- 14.08
+      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 0x7ff899d749d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff899d74a60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff899d74af0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff899d74b80>", "_build": "<function ActorCriticPolicy._build at 0x7ff899d74c10>", "forward": "<function ActorCriticPolicy.forward at 0x7ff899d74ca0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff899d74d30>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff899d74dc0>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff899d74e50>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff899d74ee0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff899d74f70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff899d75000>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ff899d8a500>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 20054016, "_total_timesteps": 20000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1699565508320164653, "learning_rate": 0.0, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVswAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiS0CFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0027007999999999477, "_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": 1224, "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": 64, "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-5.15.0-88-generic-x86_64-with-glibc2.35 # 98-Ubuntu SMP Mon Oct 2 15:18:56 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.26.1", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1"}}

ppo-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdbce25340366f34c9ec3e97cca5c51959b78ecebd1ca6e254624dc4e7029b8b
+size 146878

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 0x7ff899d749d0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff899d74a60>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff899d74af0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff899d74b80>",
+        "_build": "<function ActorCriticPolicy._build at 0x7ff899d74c10>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7ff899d74ca0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff899d74d30>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff899d74dc0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7ff899d74e50>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff899d74ee0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff899d74f70>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff899d75000>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7ff899d8a500>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 20054016,
+    "_total_timesteps": 20000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1699565508320164653,
+    "learning_rate": 0.0,
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVswAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAABAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiS0CFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.0027007999999999477,
+    "_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": 1224,
+    "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": 64,
+    "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 sha256:8471146ed46d072feb7479bd431b5f1f4e3d49f81f5c95bc8c9c710ddade8c6a
+size 88490

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:381cc72ecc522d14d2b2f338d477f9d5a5b0cda4f27cd4e87622b043d3af2ece
+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 +1,8 @@
+- OS: Linux-5.15.0-88-generic-x86_64-with-glibc2.35 # 98-Ubuntu SMP Mon Oct 2 15:18:56 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.1.0+cu121
+- GPU Enabled: True
+- Numpy: 1.26.1
+- Cloudpickle: 3.0.0
+- Gymnasium: 0.28.1

results.json

@@ -0,0 +1 @@
+{"mean_reward": 283.5360348967889, "std_reward": 14.083706826564907, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-10T11:29:40.335038"}