Upload PPO LunarLander-v2 trained agent

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,35 +1,37 @@
 ---
-library_name: ml-agents
+library_name: stable-baselines3
 tags:
-- Huggy
+- LunarLander-v2
 - deep-reinforcement-learning
 - reinforcement-learning
-- ML-Agents-Huggy
+- 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: 252.32 +/- 37.46
+      name: mean_reward
+      verified: false
 ---
 
-  # **ppo** Agent playing **Huggy**
-  This is a trained model of a **ppo** agent playing **Huggy**
-  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+# **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 ML-Agents)
-  The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
+## Usage (with Stable-baselines3)
+TODO: Add your code
 
-  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
-  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
-  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
-  - A *longer tutorial* to understand how works ML-Agents:
-  https://huggingface.co/learn/deep-rl-course/unit5/introduction
 
-  ### Resume the training
-  ```bash
-  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
-  ```
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
 
-  ### Watch your Agent play
-  You can watch your agent **playing directly in your browser**
-
-  1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
-  2. Step 1: Find your model_id: canyuzzz/ppo-Huggy
-  3. Step 2: Select your *.nn /*.onnx file
-  4. Click on Watch the agent play 👀
-  
+...
+```

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 200000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 15, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 1000, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 120, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Huggy", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"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 0x78282bd7e520>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78282bd7e5c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78282bd7e660>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78282bd7e700>", "_build": "<function ActorCriticPolicy._build at 0x78282bd7e7a0>", "forward": "<function ActorCriticPolicy.forward at 0x78282bd7e840>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x78282bd7e8e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78282bd7e980>", "_predict": "<function ActorCriticPolicy._predict at 0x78282bd7ea20>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78282bd7eac0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78282bd7eb60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x78282bd7ec00>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78282be39a00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1770618937185173483, "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:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "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-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025", "Python": "3.12.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.9.0+cu126", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.2", "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 sha256:6ca2b3b08a5d1033fb15a6455fae1cd6b2ff573a6d283fbd3537df506b050a2b
+size 149175

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 0x78282bd7e520>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78282bd7e5c0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78282bd7e660>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78282bd7e700>",
+        "_build": "<function ActorCriticPolicy._build at 0x78282bd7e7a0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x78282bd7e840>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x78282bd7e8e0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78282bd7e980>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x78282bd7ea20>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78282bd7eac0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78282bd7eb60>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x78282bd7ec00>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x78282be39a00>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1770618937185173483,
+    "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:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="
+    },
+    "_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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu",
+        "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:": "gAWV1gIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwiVAZcAiQFTAJROhZQpjAFflIWUjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEyL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUS4RDCPiAANgPEogKlEMAlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTIvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpRoAIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCF9lH2UKGgYjARmdW5jlIwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBmMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP8mZmZmZmZqFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
+    },
+    "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 sha256:767c64f1334aae9678905d93f17f6ce338131aa7c356f62d5b750ce33969d545
+size 88695

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b7fba678e7845fe88336b08ce47bdbfa2d71c5fc6c9bac7c084691a9438b937
+size 44095

ppo-LunarLander-v2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c7431cf6005e7d8f367d79e995f63e2f9b981a37e3437b795d058f9af4308b
+size 1261

ppo-LunarLander-v2/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025
+- Python: 3.12.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.9.0+cu126
+- GPU Enabled: True
+- Numpy: 2.0.2
+- Cloudpickle: 3.1.2
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7840ffe82168643e456b8bb3a2b42f74e5aab80e6b054b2c3b4736e78da53e4
+size 165196

results.json

@@ -0,0 +1 @@
+{"mean_reward": 252.32392319999994, "std_reward": 37.46407036949538, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-09T06:58:59.057787"}