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: 267.09 +/- 26.12
+      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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7f815eac4160>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f815eac41f0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f815eac4280>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f815eac4310>", "_build": "<function ActorCriticPolicy._build at 0x7f815eac43a0>", "forward": "<function ActorCriticPolicy.forward at 0x7f815eac4430>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f815eac44c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f815eac4550>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f815eac45e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f815eac4670>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f815eac4700>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f815eabf600>"}, "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": 16384, "_total_timesteps": 100, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670321521865615216, "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": -162.84, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 252, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.1+cu113", "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 sha256:88b4a9a28134a91f802cd27dddffae1f598f6414d8e4a67f9fb8351037cf5a75
+size 144742

ppo-LunarLander-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+1.6.2

ppo-LunarLander-v2/data

@@ -0,0 +1,94 @@
+{
+    "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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7f815eac4160>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f815eac41f0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f815eac4280>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f815eac4310>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f815eac43a0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f815eac4430>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f815eac44c0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f815eac4550>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f815eac45e0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f815eac4670>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f815eac4700>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f815eabf600>"
+    },
+    "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": 16384,
+    "_total_timesteps": 100,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1670321521865615216,
+    "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": -162.84,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVfQkAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMI19mQf2bSUECUhpRSlIwBbJRLr4wBdJRHQMA+eGV7hNx1fZQoaAZoCWgPQwh2NXnKqrdxQJSGlFKUaBVL02gWR0DAPp0rTYukdX2UKGgGaAloD0MIcTjzq/k4c0CUhpRSlGgVS99oFkdAwD6q46Oo53V9lChoBmgJaA9DCBUb8zpiaHFAlIaUUpRoFUvmaBZHQMA+snXumaZ1fZQoaAZoCWgPQwgxI7w9iK1wQJSGlFKUaBVL6WgWR0DAPrVchTwVdX2UKGgGaAloD0MImUf+YCAocUCUhpRSlGgVS+loFkdAwD61QpF1CHV9lChoBmgJaA9DCIknu5nRyG1AlIaUUpRoFUv1aBZHQMA+wQeFL391fZQoaAZoCWgPQwjRXRJnBUVxQJSGlFKUaBVL+mgWR0DAPsWc8TzvdX2UKGgGaAloD0MIqODwgshDcUCUhpRSlGgVTQkBaBZHQMA+0sPJ7sx1fZQoaAZoCWgPQwi+iSE5mTJuQJSGlFKUaBVNDAFoFkdAwD7VSOzY3HV9lChoBmgJaA9DCJsBLsiWkm5AlIaUUpRoFU0WAWgWR0DAPtylchTwdX2UKGgGaAloD0MIkzZV98h/cECUhpRSlGgVTSIBaBZHQMA+5h2OhkB1fZQoaAZoCWgPQwhbBpylJOJxQJSGlFKUaBVNNgFoFkdAwD71ixVyWHV9lChoBmgJaA9DCM2QKoqX9nFAlIaUUpRoFU09AWgWR0DAPvsETxoadX2UKGgGaAloD0MIG9XpQNa+ckCUhpRSlGgVTWABaBZHQMA/FpNj9XN1fZQoaAZoCWgPQwjNPLmmQANwQJSGlFKUaBVNswFoFkdAwD9bORkmQnV9lChoBmgJaA9DCLFuvDuyHnFAlIaUUpRoFUvvaBZHQMA/aKG+K0l1fZQoaAZoCWgPQwgs2EY8WblyQJSGlFKUaBVNJAFoFkdAwD94oKlYU3V9lChoBmgJaA9DCO+pnPYU0W5AlIaUUpRoFUvuaBZHQMA/iN52Qnx1fZQoaAZoCWgPQwhI/fUKCyJwQJSGlFKUaBVNCAFoFkdAwD+NXgccVHV9lChoBmgJaA9DCLBx/bs+7W9AlIaUUpRoFUvsaBZHQMA/mloUSIx1fZQoaAZoCWgPQwga+FENuzRwQJSGlFKUaBVL32gWR0DAP5oNAkcCdX2UKGgGaAloD0MIlX1XBP/bcUCUhpRSlGgVS/xoFkdAwD+bQ3xWk3V9lChoBmgJaA9DCGglrfgGT3NAlIaUUpRoFU0YAWgWR0DAP6Ql2NeddX2UKGgGaAloD0MIMV2I1d8Fc0CUhpRSlGgVTSMBaBZHQMA/qu8TSLJ1fZQoaAZoCWgPQwgwRiQKLRBxQJSGlFKUaBVL7GgWR0DAP65KaodddX2UKGgGaAloD0MI4dIx55ksb0CUhpRSlGgVS+JoFkdAwD+7N+so2HV9lChoBmgJaA9DCMNF7ulqb3FAlIaUUpRoFU0YAWgWR0DAP79tO2y+dX2UKGgGaAloD0MIWWyTikb9cECUhpRSlGgVS/NoFkdAwD/COFQEZHV9lChoBmgJaA9DCOz4LxCEL25AlIaUUpRoFU1BAWgWR0DAP8L0jC53dX2UKGgGaAloD0MIYaQXtXvZcUCUhpRSlGgVTRoBaBZHQMA/94ku6Et1fZQoaAZoCWgPQwjNc0S+yy1zQJSGlFKUaBVL1mgWR0DAQDPeYUnHdX2UKGgGaAloD0MIprc/Fw0mckCUhpRSlGgVTQsBaBZHQMBARI/zJ6p1fZQoaAZoCWgPQwhw7NlzmWJtQJSGlFKUaBVNCgFoFkdAwEBUhIOH33V9lChoBmgJaA9DCAkWhzO/JnFAlIaUUpRoFUv9aBZHQMBAV/wiJO51fZQoaAZoCWgPQwhp5V5gVrZwQJSGlFKUaBVL9mgWR0DAQGJx3mmtdX2UKGgGaAloD0MIgUI9fcRwcUCUhpRSlGgVS/doFkdAwEBkJokAxXV9lChoBmgJaA9DCFjhlo9k03BAlIaUUpRoFUvwaBZHQMBAbrRKHwh1fZQoaAZoCWgPQwghIF9CBQtyQJSGlFKUaBVL22gWR0DAQHif4AS4dX2UKGgGaAloD0MIk8SScvdecECUhpRSlGgVS+toFkdAwEB9J5E+gXV9lChoBmgJaA9DCPxtT5DY8W9AlIaUUpRoFU0VAWgWR0DAQIb9ycTbdX2UKGgGaAloD0MIigW+oltkckCUhpRSlGgVTQgBaBZHQMBAht0/4Zd1fZQoaAZoCWgPQwjlRSbgl5ZyQJSGlFKUaBVL9WgWR0DAQIpbjcVQdX2UKGgGaAloD0MIG53zUxxpckCUhpRSlGgVTW0BaBZHQMBAjzF2mpF1fZQoaAZoCWgPQwgUsYhhB+dwQJSGlFKUaBVNXgFoFkdAwECyiaiKznV9lChoBmgJaA9DCOdtbHakQXBAlIaUUpRoFU04AWgWR0DAQLzpzLfUdX2UKGgGaAloD0MIdR4V/3c3b0CUhpRSlGgVTQoBaBZHQMBA1jSG8Ep1fZQoaAZoCWgPQwhwmdNlMRRzQJSGlFKUaBVL32gWR0DAQPZtix3WdX2UKGgGaAloD0MIOZ1kq0tnc0CUhpRSlGgVS/JoFkdAwED5ddmg8XV9lChoBmgJaA9DCLTKTGn96m9AlIaUUpRoFUvXaBZHQMBA/SvcJt11fZQoaAZoCWgPQwhodXKGYptuQJSGlFKUaBVL6WgWR0DAQRl74SHudX2UKGgGaAloD0MI3lZ6bbZDb0CUhpRSlGgVS+xoFkdAwEEdqLS/kHV9lChoBmgJaA9DCFJ/vcJCMHBAlIaUUpRoFU0CAWgWR0DAQSYplSTAdX2UKGgGaAloD0MIaFpiZTQXcECUhpRSlGgVS+ZoFkdAwEEs/M4cWHV9lChoBmgJaA9DCJQVw9WBkm9AlIaUUpRoFUvXaBZHQMBBMW0iQkp1fZQoaAZoCWgPQwhZhc0A1+dwQJSGlFKUaBVL/GgWR0DAQTVBF/hEdX2UKGgGaAloD0MI3NYWntfIcECUhpRSlGgVS9hoFkdAwEE3SuyNXHVlLg=="
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 252,
+    "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-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ce19d8ed4e314d4522b20eb7b28b44e247f57d6658167f1356383069941ccfb
+size 87865

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92856e8bf2d2c502c9e476ceb57cc6c923bd456ecfad3e30afa08b19d6c358f8
+size 43201

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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
+Python: 3.8.15
+Stable-Baselines3: 1.6.2
+PyTorch: 1.12.1+cu113
+GPU Enabled: True
+Numpy: 1.21.6
+Gym: 0.21.0

results.json

@@ -0,0 +1 @@
+{"mean_reward": 267.0861641632625, "std_reward": 26.12388280942646, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-06T10:13:04.369300"}