first-tutorial

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLander-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: MlpPolicy
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 279.95 +/- 24.57
+      name: mean_reward
+      verified: false
+---
+
+# **MlpPolicy** Agent playing **LunarLander-v2**
+This is a trained model of a **MlpPolicy** 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 0x7d79a3195630>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d79a31956c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d79a3195750>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d79a31957e0>", "_build": "<function ActorCriticPolicy._build at 0x7d79a3195870>", "forward": "<function ActorCriticPolicy.forward at 0x7d79a3195900>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d79a3195990>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d79a3195a20>", "_predict": "<function ActorCriticPolicy._predict at 0x7d79a3195ab0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d79a3195b40>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d79a3195bd0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d79a3195c60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d79a3130740>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1720059786718010948, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAM3l57wvpIw+RsRgPmYVbb6zlxs9FBYaPAAAAAAAAAAAII1HvgOMdD895Xm95PPrvp2riL5f5Es9AAAAAAAAAAAa5d+998njPmhYID50H6m+XFPhPGvuv7wAAAAAAAAAADPzAj22OSi8S6MDurdOdjwARow9a3pNvQAAgD8AAIA/mnL6vHX7tz9mogC/ws4EPgIL3jweiTA9AAAAAAAAAAC6+1y+VHsfP4S6IT72Fsu+pjgkvkihzz0AAAAAAAAAAID9GD60vwQ+7EiyvaR0nr5dp/S8hcnTPAAAAAAAAAAAAEAuPKNARD3Q0ms90GpmvsnO7DximGm9AAAAAAAAAABmuDc8D4svvI0Fvju2ihQ9wRigPb1W7r0AAIA/AACAP80g4DvrcrQ/bVoxPwLUU70vvgG8TrEgvgAAAAAAAAAA7Tcxvp/lbD9ZoBW+LsDkvggHLL7stgA+AAAAAAAAAAAmwFY+MEmXPjKQer6VX4e+ZzqOu3v/670AAAAAAAAAALOHAb2uWoO8DGCBu5cvuTzeO+o9ZzGTvQAAgD8AAIA/Gkx+PaGWdT66NSG+gFuVvmYMKr1vJMA9AAAAAAAAAAAzrwY+no4UP0tIsr36vrm+o/bKu0puUL0AAAAAAAAAAABoazt0bM8+/nb6PVHyir4ImkM9HnljvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAEAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": 300, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "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:ddbd43df2bada7759a497ae788d24a4f67c6cb326463a5095af6e96e87d5502a
+size 148016

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 0x7d79a3195630>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d79a31956c0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d79a3195750>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d79a31957e0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7d79a3195870>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7d79a3195900>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d79a3195990>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d79a3195a20>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7d79a3195ab0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d79a3195b40>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d79a3195bd0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d79a3195c60>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7d79a3130740>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1720059786718010948,
+    "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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAEAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": 300,
+    "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "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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"
+    }
+}

ppo-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9debdae03f183544a1700bac6a9bb4c49c8b08e058e7925ea6394121c1bfe3
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e2e7d45dd1c2d1aaf8788913a6070c7404232c2bf96e68bbdec4a23a61dc116
+size 43762

ppo-LunarLander-v2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

ppo-LunarLander-v2/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.3.0+cu121
+- GPU Enabled: True
+- Numpy: 1.25.2
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": 279.95436609999996, "std_reward": 24.573384762264663, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-04T02:46:55.921037"}