Try PPO algorithm

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: 271.17 +/- 17.19
+      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 0x7f5b8934dd30>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5b8934ddc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5b8934de50>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5b8934dee0>", "_build": "<function ActorCriticPolicy._build at 0x7f5b8934df70>", "forward": "<function ActorCriticPolicy.forward at 0x7f5b89351040>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f5b893510d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5b89351160>", "_predict": "<function ActorCriticPolicy._predict at 0x7f5b893511f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5b89351280>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5b89351310>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5b893513a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f5b89347cf0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1676726095192916394, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAADMtrwpKF66/QsnuHdVJrOalDe6CFRENwAAgD8AAIA/U90TvvbnRzsLnBe65/xCN64v9rwzTjs5AACAPwAAgD9zHf+9vGMSP/DAZj16D5K+QNUWPQ4IlbsAAAAAAAAAAJqlvb1Iq6661WWROF2XojNDpbI5mnamtwAAgD8AAIA/APbhvEhngLpyo4c1InLvLZ0pzrq66LW0AACAPwAAgD9NalC9j/Z/ujBskTsi4nQyn+zsueq3qboAAIA/AACAP9NIAL4Bvas9SHBIPVMHT776ZpU8xcnYuwAAAAAAAAAAE08Yvo8GZjvXRhk8xPMXulS0Hr097Qg7AACAPwAAgD/AM7e9KWw1ujpbZzzQk9Y2NhM4uxM80zUAAAAAAACAP5rEjzyupaS6NU05N6/0EzL8Yaq6vhNUtgAAgD8AAIA/Gj6VPVxTf7raJ8I69ZecNfCMwLqe1OK5AAAAAAAAAADahSI+OLi/uxqQrblj5zo3Gm0yvW630zgAAIA/AACAPwByB7z21H+6+SwXOSAwFTS9vPI5xnAwuAAAgD8AAIA/AClMPcMRTroO26G6lHAltrgO+jkS4ro5AACAPwAAgD/Gfya+DX4AP+4S/D0zUIq+lgqYPAKljz0AAAAAAAAAADDDer47WRk/u62pvSTH0L4AkdC9w7WQvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "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:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

ppo_cartpole.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:071bdaf3351d026453ef5cb0bd0fdd09a749fc87240bcc610f76e21e5dc1dae5
+size 147416

ppo_cartpole/_stable_baselines3_version

@@ -0,0 +1 @@
+1.7.0

ppo_cartpole/data

@@ -0,0 +1,95 @@
+{
+    "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 0x7f5b8934dd30>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5b8934ddc0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5b8934de50>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5b8934dee0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f5b8934df70>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f5b89351040>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f5b893510d0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5b89351160>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f5b893511f0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5b89351280>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5b89351310>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5b893513a0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f5b89347cf0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            8
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 4,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1676726095192916394,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_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,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 248,
+    "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
+}

ppo_cartpole/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d9d2abdebbb3f9129bcf266e443f3f768ac6afd48cffa5f4399fa4a74f8b9b8
+size 87929

ppo_cartpole/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cf3c3d616b6b5f02d544db0a20f7ff3ab29d2c8abaf0ea2cf0ad9e5aa86fd6e
+size 43393

ppo_cartpole/pytorch_variables.pth

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

ppo_cartpole/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
+- Python: 3.8.10
+- Stable-Baselines3: 1.7.0
+- PyTorch: 1.13.1+cu116
+- GPU Enabled: True
+- Numpy: 1.21.6
+- Gym: 0.21.0

results.json

@@ -0,0 +1 @@
+{"mean_reward": 271.1695162594388, "std_reward": 17.18993322050464, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-18T13:47:42.803894"}