LunarLander MLP 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-MLP
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 246.46 +/- 32.22
+      name: mean_reward
+      verified: false
+---
+
+# **PPO-MLP** Agent playing **LunarLander-v2**
+This is a trained model of a **PPO-MLP** 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 0x7c5663374b80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c5663374c10>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c5663374ca0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c5663374d30>", "_build": "<function ActorCriticPolicy._build at 0x7c5663374dc0>", "forward": "<function ActorCriticPolicy.forward at 0x7c5663374e50>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c5663374ee0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c5663374f70>", "_predict": "<function ActorCriticPolicy._predict at 0x7c5663375000>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c5663375090>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c5663375120>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c56633751b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c5663315d00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1701627363031436168, "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": 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-5.15.120+-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-Liog.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a298df534d30c1110e6b5912b4b746a9be0a991981d377ec638bc9076130d4f6
+size 147206

ppo-LunarLander-v2-Liog/_stable_baselines3_version

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

ppo-LunarLander-v2-Liog/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 0x7c5663374b80>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c5663374c10>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c5663374ca0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c5663374d30>",
+        "_build": "<function ActorCriticPolicy._build at 0x7c5663374dc0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7c5663374e50>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c5663374ee0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c5663374f70>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7c5663375000>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c5663375090>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c5663375120>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c56633751b0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7c5663315d00>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1701627363031436168,
+    "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": 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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"
+    }
+}

ppo-LunarLander-v2-Liog/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e5d55885b9431598a244fc74a1b445b1ae2941509f50603a3068046a49dc7cd
+size 88490

ppo-LunarLander-v2-Liog/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbac17a1d19c35bcc605f4d145df0e7b97815626852b901cb5b2eec0bd84fef1
+size 43762

ppo-LunarLander-v2-Liog/pytorch_variables.pth

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

ppo-LunarLander-v2-Liog/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": 246.4551019, "std_reward": 32.223107933639355, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-03T18:48:29.809568"}