first commit ppo for lunarlander

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: -1687.94 +/- 1928.51
+      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 0x7fceaca0e950>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fceaca0e9e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fceaca0ea70>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fceaca0eb00>", "_build": "<function ActorCriticPolicy._build at 0x7fceaca0eb90>", "forward": "<function ActorCriticPolicy.forward at 0x7fceaca0ec20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fceaca0ecb0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fceaca0ed40>", "_predict": "<function ActorCriticPolicy._predict at 0x7fceaca0edd0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fceaca0ee60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fceaca0eef0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fceaca0ef80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fceaca14880>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 32768, "_total_timesteps": 100, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1690323923026048700, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAABAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -326.68, "_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": 10, "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.6", "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": -1687.9426996000002, "std_reward": 1928.5132597531233, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-25T23:33:54.047283"}

test.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa98a3345a72ced64f4052165828011e5dd65185170dda74cd56f7793dbe25d2
+size 145856

test/_stable_baselines3_version

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

test/data

@@ -0,0 +1,96 @@
+{
+    "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 0x7fceaca0e950>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fceaca0e9e0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fceaca0ea70>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fceaca0eb00>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fceaca0eb90>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fceaca0ec20>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fceaca0ecb0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fceaca0ed40>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fceaca0edd0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fceaca0ee60>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fceaca0eef0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fceaca0ef80>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fceaca14880>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 32768,
+    "_total_timesteps": 100,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1690323923026048700,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAABAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -326.68,
+    "_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": 10,
+    "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "n_steps": 2048,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 10,
+    "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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"
+    }
+}

test/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d0c6b7545dea933880b3fc5d70088a6c4dce956906bca1659e96bd96f096d64
+size 88057

test/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:283889f5ce9b0189effd63296dce859c8bb9fa70126d7c57c244f7b743b24a7a
+size 43329

test/pytorch_variables.pth

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

test/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023
+- Python: 3.10.6
+- 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