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: 252.82 +/- 24.57
+      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 0x7f175d598e50>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f175d598ee0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f175d598f70>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f175d599000>", "_build": "<function ActorCriticPolicy._build at 0x7f175d599090>", "forward": "<function ActorCriticPolicy.forward at 0x7f175d599120>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f175d5991b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f175d599240>", "_predict": "<function ActorCriticPolicy._predict at 0x7f175d5992d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f175d599360>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f175d5993f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f175d599480>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f175d591200>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1685139693903733259, "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": -0.015808000000000044, "_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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "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-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "False", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-1m-mlp.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a8451478cbcf0a0a93014b26656c5bd8d99302eec7b8473b4ed7c685d015062
+size 146244

ppo-1m-mlp/_stable_baselines3_version

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

ppo-1m-mlp/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 0x7f175d598e50>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f175d598ee0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f175d598f70>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f175d599000>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f175d599090>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f175d599120>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f175d5991b0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f175d599240>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f175d5992d0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f175d599360>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f175d5993f0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f175d599480>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f175d591200>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1685139693903733259,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAGZ+Wr3DfUK6Y4EuOu8+ErO7o6K7IAFLuQAAgD8AAIA/s2tnPcPReLq9muU6VW28NYA0XrvJLQa6AACAPwAAgD8ADLs7cW0buc1F8jTCEdUvWKGfuobLULQAAIA/AACAP2bUF742Rh28zyk0u8dANLkIK4k9QLtwOgAAgD8AAIA/M4iWPE/lGbx2o7M7ZpIrPFVufr2uwBM9AACAPwAAgD/mKXm9w4keunN27TqAYzE2PpubuH3CC7oAAIA/AACAPw3MzL1cb366YpbKuSpRCLaZiS07HvHpOAAAgD8AAIA/AHBHPSkYbrpef+u68yvUtXTvNDpdBQo6AACAPwAAgD8AMne9ct6gP7f3OL4OdJy+lFfavV1NiD0AAAAAAAAAAAC0cjx76qC6UFO8ugT4obVDYM25BojYOQAAgD8AAIA/zRPrPOFol7rifDO4YCITs1zkzbruSk83AACAPwAAgD8Ariw8FDyPuj4YOTq8e/W1LaqGugjrU7kAAIA/AACAP2YWWTuFG8y52uPcOrdot7V/hQC80yICugAAgD8AAIA/mvcbPnZKGLzalCS7YuTKOeA1gb2FxYY6AACAPwAAgD/NUVc9SD+Tumsv3TrVy4w1GlbQuhsZALoAAIA/AACAP2bnCL0UqIO6JqhMucnJUrTyvoM5nettOAAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": 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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "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-1m-mlp/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:657e64cb1b5657b53ce91218e9eb933f98697885105acd26f45ca8769ea7d67a
+size 87545

ppo-1m-mlp/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae48c5027c6b4e65e94033d3268aeb4b4308165108f303209808ea1ca9ae8998
+size 43201

ppo-1m-mlp/pytorch_variables.pth

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

ppo-1m-mlp/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023
+- Python: 3.10.11
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.0.1+cu118
+- GPU Enabled: False
+- Numpy: 1.22.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": 252.82417626618673, "std_reward": 24.567893102496047, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-26T22:59:08.506991"}