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: -143.84 +/- 39.11
+      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 0x7f2c83dca050>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2c83dca0e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2c83dca170>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2c83dca200>", "_build": "<function ActorCriticPolicy._build at 0x7f2c83dca290>", "forward": "<function ActorCriticPolicy.forward at 0x7f2c83dca320>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f2c83dca3b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2c83dca440>", "_predict": "<function ActorCriticPolicy._predict at 0x7f2c83dca4d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2c83dca560>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2c83dca5f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2c83dca680>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f2c83fc6b40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 16384, "_total_timesteps": 100, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1685732748572717482, "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": -162.84, "_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": 56, "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": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81861878e470530643c2c7be877f45e8a5b29e66e527e7fc9bac2f5639c297d1
+size 144010

ppo-LunarLander-v2/_stable_baselines3_version

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

ppo-LunarLander-v2/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 0x7f2c83dca050>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2c83dca0e0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2c83dca170>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2c83dca200>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f2c83dca290>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f2c83dca320>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f2c83dca3b0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2c83dca440>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f2c83dca4d0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2c83dca560>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2c83dca5f0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2c83dca680>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f2c83fc6b40>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 16384,
+    "_total_timesteps": 100,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1685732748572717482,
+    "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": -162.84,
+    "_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": 56,
+    "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

ppo-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a77745e2e1f806db2c5f6b4e46f731f6f9d678e6fe912f24a76bc65f17379b
+size 87929

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e62a255ae35e0827b39877a3a8804fe305445acee2f965e28048add80dd8a61
+size 43329

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 +1,9 @@
+- 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: True
+- Numpy: 1.22.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": -143.83767775914603, "std_reward": 39.10681511056247, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-02T19:21:02.937035"}