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: 263.32 +/- 18.08
+      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 0x7d7712cfd1b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d7712cfd240>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d7712cfd2d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d7712cfd360>", "_build": "<function ActorCriticPolicy._build at 0x7d7712cfd3f0>", "forward": "<function ActorCriticPolicy.forward at 0x7d7712cfd480>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d7712cfd510>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d7712cfd5a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7d7712cfd630>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d7712cfd6c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d7712cfd750>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d7712cfd7e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d77134a00c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2031616, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1702233996997803603, "learning_rate": 5e-05, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAALOFL72PEHQ7kpFPPktnTL7UrX891OmjvgAAAAAAAIA/+vcBPoRn9z2GrV6+vEZjvvjO+rxWuJ89AAAAAAAAAAD6SxM+bER9PzcCDj4S7wW/vpxTPu+OFz0AAAAAAAAAAAAAi7kEa8s9g/nSPN0zbb7819c8bjPcvAAAAAAAAAAAoF5evuKWHz/V0WY+1pmlvoHrXL0aCQk+AAAAAAAAAAAzA0291/NaubYogbmCsRy17OKzO/dRmTgAAIA/AACAPxpzub278Jw/ar/OvjW6A78Azvm99dl7vgAAAAAAAAAAZoWIPeE65rjDtMq2ybDCsUlNKzuWHvA1AACAPwAAgD9zl/E9fs+FPynvsz5knR+/CJ8fPiqnmD0AAAAAAAAAADN1uzzyjrU/GE4QPtwWVL4Vvqk8MyAYvQAAAAAAAAAAgAglvZmnqz6lUh+9m1aDvoRYW70AM2y8AAAAAAAAAADNOIw7pAA3Oha2Fr3BPye+mSlqvJ5Jj70AAAAAAAAAAM3u9z1xcNE+MyYQvU1Npr6PT5884xRHPQAAAAAAAAAAmkf1vEszCT+lvau81xC8vgaMi7zjWVS9AAAAAAAAAADmhiY+c0tYP1iDXz7Knhq/heaHPlgsoD0AAAAAAAAAAI0M7z2V7OU+nwohvrafrL5O5rw8LCCevQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_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": 620, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 2048, "gamma": 0.9999, "gae_lambda": 0.99, "ent_coef": 0.01, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2-finetuned.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363b824a271ebffce9f66d65524f819c91c4bbc265ba30c8b596e58625d361cd
+size 148011

ppo-LunarLander-v2-finetuned/_stable_baselines3_version

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

ppo-LunarLander-v2-finetuned/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 0x7d7712cfd1b0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d7712cfd240>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d7712cfd2d0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d7712cfd360>",
+        "_build": "<function ActorCriticPolicy._build at 0x7d7712cfd3f0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7d7712cfd480>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d7712cfd510>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d7712cfd5a0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7d7712cfd630>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d7712cfd6c0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d7712cfd750>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d7712cfd7e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7d77134a00c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 2031616,
+    "_total_timesteps": 2000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1702233996997803603,
+    "learning_rate": 5e-05,
+    "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": -0.015808000000000044,
+    "_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": 620,
+    "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "n_steps": 2048,
+    "gamma": 0.9999,
+    "gae_lambda": 0.99,
+    "ent_coef": 0.01,
+    "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,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

ppo-LunarLander-v2-finetuned/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:750c48240adf3bb25fcdadc46d95168fab286c38dd470dea569843e0371a860f
+size 88362

ppo-LunarLander-v2-finetuned/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ef9fe9c22fa99ed9995ad224f1303bb96bb83d16d494e6c373b79d2f495c069
+size 43762

ppo-LunarLander-v2-finetuned/pytorch_variables.pth

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

ppo-LunarLander-v2-finetuned/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.1.0+cu118
+- GPU Enabled: True
+- Numpy: 1.23.5
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": 263.32383033729104, "std_reward": 18.075275964888394, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-10T19:46:02.155845"}