my first RL!

LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03572ba2ceab790b0df5c25d71919e3c2a3ecf3c4db8a8285d1a1313fc364c2d
+size 145644

LunarLander-v2/_stable_baselines3_version

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

LunarLander-v2/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 0x7f12f67580d0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f12f6758160>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f12f67581f0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f12f6758280>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f12f6758310>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f12f67583a0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f12f6758430>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f12f67584c0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f12f6758550>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f12f67585e0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f12f6758670>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f12f6758700>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f12f6942700>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1686797513996268308,
+    "learning_rate": 0.0,
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_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,
+    "_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": 256,
+    "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,
+    "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": 1,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b1efc6f7703916a104d0cec926215dc7498c1962ac0d81498f1aad6547c2468
+size 88057

LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbca7d55e4f09d5f8288816716aa1a13d4758d55d67694bd52bd2eaf1d4ba4da
+size 43329

LunarLander-v2/pytorch_variables.pth

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

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: 3.10.12
+- 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

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: 247.75 +/- 17.41
+      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 0x7f12f67580d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f12f6758160>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f12f67581f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f12f6758280>", "_build": "<function ActorCriticPolicy._build at 0x7f12f6758310>", "forward": "<function ActorCriticPolicy.forward at 0x7f12f67583a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f12f6758430>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f12f67584c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f12f6758550>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f12f67585e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f12f6758670>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f12f6758700>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f12f6942700>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1686797513996268308, "learning_rate": 0.0, "tensorboard_log": null, "_last_obs": null, "_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, "_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": 256, "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, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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": 1, "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": "3.10.12", "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": 247.75294040000003, "std_reward": 17.407447395956503, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-15T04:22:05.862302"}