My First RL Agent

README.md

@@ -1,3 +1,37 @@
----
-license: apache-2.0
----
+---
+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: 237.89 +/- 32.98
+      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 0x78f8e96bee80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78f8e96bef20>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78f8e96befc0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78f8e96bf060>", "_build": "<function ActorCriticPolicy._build at 0x78f8e96bf100>", "forward": "<function ActorCriticPolicy.forward at 0x78f8e96bf1a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x78f8e96bf240>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78f8e96bf2e0>", "_predict": "<function ActorCriticPolicy._predict at 0x78f8e96bf380>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78f8e96bf420>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78f8e96bf4c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x78f8e96bf560>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78f8ea7e5f00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1737624297981806868, "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": 248, "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:": "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": "3.11.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "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:f1c35a4f715942d1423ebbfccbd64864e436ac1a2c72420d725e1d2e63180753
+size 148128

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 0x78f8e96bee80>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78f8e96bef20>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78f8e96befc0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78f8e96bf060>",
+        "_build": "<function ActorCriticPolicy._build at 0x78f8e96bf100>",
+        "forward": "<function ActorCriticPolicy.forward at 0x78f8e96bf1a0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x78f8e96bf240>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78f8e96bf2e0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x78f8e96bf380>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78f8e96bf420>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78f8e96bf4c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x78f8e96bf560>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x78f8ea7e5f00>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1737624297981806868,
+    "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": 248,
+    "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:": "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 sha256:26168fd4bd480c8c5be920aff78a8d6d2eacf4ca7a20a531a5ea4956fa829b0d
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77c350d404c8fe3c55e208c060fa2eb0b23f40ecb0ad5e0509d2cf3d2cfa67f1
+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: 3.11.11
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.5.1+cu121
+- GPU Enabled: True
+- Numpy: 1.26.4
+- Cloudpickle: 3.1.0
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": 237.8894909, "std_reward": 32.9781680826646, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-23T09:53:00.784785"}