upload PPO 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: -262.98 +/- 209.30
+      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 0x7f6e853089d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6e85308a60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6e85308af0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6e85308b80>", "_build": "<function ActorCriticPolicy._build at 0x7f6e85308c10>", "forward": "<function ActorCriticPolicy.forward at 0x7f6e85308ca0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f6e85308d30>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6e85308dc0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f6e85308e50>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6e85308ee0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6e85308f70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6e8530c040>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f6e8530a0f0>"}, "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:": "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", "n": 4, "_shape": [], "dtype": "int64", "_np_random": "RandomState(MT19937)"}, "n_envs": 1, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": null, "learning_rate": 0.005, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "n_steps": 1024, "gamma": 0.99, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "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-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:763b971813c5d5e15f9b07fa61ae0af9dc8a0f0bbf0fd35a77d014ac41f185be
+size 56730

ppo-LunarLander-v2/_stable_baselines3_version

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

ppo-LunarLander-v2/data

@@ -0,0 +1,83 @@
+{
+    "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 0x7f6e853089d0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6e85308a60>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6e85308af0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6e85308b80>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f6e85308c10>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f6e85308ca0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f6e85308d30>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6e85308dc0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f6e85308e50>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6e85308ee0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6e85308f70>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6e8530c040>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f6e8530a0f0>"
+    },
+    "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:": "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",
+        "n": 4,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 0,
+    "_total_timesteps": 0,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": null,
+    "learning_rate": 0.005,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/dHrhR64Ue4WUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="
+    },
+    "_last_obs": null,
+    "_last_episode_starts": null,
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 1,
+    "ep_info_buffer": null,
+    "ep_success_buffer": null,
+    "_n_updates": 0,
+    "n_steps": 1024,
+    "gamma": 0.99,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 128,
+    "n_epochs": 10,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b41ebb7477614ddb6e5d87cf0ca684e43d54d9853afccc0a6dea202783b70b8
+size 687

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2525c912651a0f2d4e73a4535aef2da19c32b0ef1b68cb8c06c59e6bc5136990
+size 43393

ppo-LunarLander-v2/pytorch_variables.pth

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

ppo-LunarLander-v2/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": -262.9771573988022, "std_reward": 209.30414828679895, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-13T02:56:14.345940"}