add a trained RL agent in LunarLander-v2 environment (trained using 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: Proximal Parity Optimization (PPO)
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 259.25 +/- 10.87
+      name: mean_reward
+      verified: false
+---
+
+# **Proximal Parity Optimization (PPO)** Agent playing **LunarLander-v2**
+This is a trained model of a **Proximal Parity Optimization (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 0x7f9aa3b9f670>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9aa3b9f700>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9aa3b9f790>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9aa3b9f820>", "_build": "<function ActorCriticPolicy._build at 0x7f9aa3b9f8b0>", "forward": "<function ActorCriticPolicy.forward at 0x7f9aa3b9f940>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f9aa3b9f9d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9aa3b9fa60>", "_predict": "<function ActorCriticPolicy._predict at 0x7f9aa3b9faf0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9aa3b9fb80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9aa3b9fc10>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9aa3b9fca0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f9aa3b8e930>"}, "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": 1673604681603675398, "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, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

lunar_lander_v2_ppo_1M_steps.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9506e89aef20bb57b29777f72fd0fe6dc77c10188de5e8fd5e3c6732df6d8f8f
+size 147408

lunar_lander_v2_ppo_1M_steps/_stable_baselines3_version

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

lunar_lander_v2_ppo_1M_steps/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 0x7f9aa3b9f670>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9aa3b9f700>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9aa3b9f790>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9aa3b9f820>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f9aa3b9f8b0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f9aa3b9f940>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f9aa3b9f9d0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9aa3b9fa60>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f9aa3b9faf0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9aa3b9fb80>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9aa3b9fc10>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9aa3b9fca0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f9aa3b8e930>"
+    },
+    "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": 1673604681603675398,
+    "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
+}

lunar_lander_v2_ppo_1M_steps/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43affdf2fd5cf4f9bb160c8c285dd8b5552fbc05d2317f15fe858a5b4621b773
+size 87929

lunar_lander_v2_ppo_1M_steps/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90bdcff46f1415c067902cc6cae68f47bed9bdf2fa3f85deb34041a92c6e03a0
+size 43393

lunar_lander_v2_ppo_1M_steps/pytorch_variables.pth

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

lunar_lander_v2_ppo_1M_steps/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.10.147+-x86_64-with-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
+- Python: 3.8.16
+- Stable-Baselines3: 1.7.0
+- PyTorch: 1.13.0+cu116
+- GPU Enabled: True
+- Numpy: 1.21.6
+- Gym: 0.21.0

results.json

@@ -0,0 +1 @@
+{"mean_reward": 259.250761749301, "std_reward": 10.873408423007765, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-13T11:21:29.412466"}