first DeepRL model

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: 208.93 +/- 77.14
+      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 0x7afed2f09630>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7afed2f096c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7afed2f09750>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7afed2f097e0>", "_build": "<function ActorCriticPolicy._build at 0x7afed2f09870>", "forward": "<function ActorCriticPolicy.forward at 0x7afed2f09900>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7afed2f09990>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7afed2f09a20>", "_predict": "<function ActorCriticPolicy._predict at 0x7afed2f09ab0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7afed2f09b40>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7afed2f09bd0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7afed2f09c60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7afed2f0c7c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1700953566343217402, "learning_rate": 0.0003, "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": 310, "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, "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-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "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:f9e3b4d74b6e4e6b3f700e3541856c381315f355bd1582f11917ff4cada764bc
+size 147209

ppo-LunarLander-v2/_stable_baselines3_version

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

ppo-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 0x7afed2f09630>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7afed2f096c0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7afed2f09750>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7afed2f097e0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7afed2f09870>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7afed2f09900>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7afed2f09990>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7afed2f09a20>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7afed2f09ab0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7afed2f09b40>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7afed2f09bd0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7afed2f09c60>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7afed2f0c7c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1700953566343217402,
+    "learning_rate": 0.0003,
+    "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": 310,
+    "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,
+    "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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"
+    }
+}

ppo-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71fba3837e9d477d349893757969d9a94b48933e06fea5dd699702e329ded590
+size 88490

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9807661fd5446d570e6cb9b6c4735b6048ec317060501407d73ceaf473441d28
+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-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.1.0+cu118
+- GPU Enabled: True
+- Numpy: 1.23.5
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": 208.93364849999998, "std_reward": 77.1359494612938, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-26T00:26:49.038175"}