Upload PPO LunarLander-v2 trained agent

Browse files

Files changed (8) hide show

README.md +27 -25
config.json +1 -1
ppo-LunarLander-v2.zip +2 -2
ppo-LunarLander-v2/data +16 -16
ppo-LunarLander-v2/policy.optimizer.pth +1 -1
ppo-LunarLander-v2/policy.pth +1 -1
replay.mp4 +0 -0
results.json +1 -1

README.md CHANGED Viewed

@@ -1,35 +1,37 @@
 ---
-library_name: ml-agents
 tags:
-- Huggy
 - deep-reinforcement-learning
 - reinforcement-learning
-- ML-Agents-Huggy
 ---
-  # **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).
-  ## Usage (with ML-Agents)
-  The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
-  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
-  ```
-  ### 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: Dhanraj1503/deep_reinforcement_learning
-  3. Step 2: Select your *.nn /*.onnx file
-  4. Click on Watch the agent play 👀

 ---
+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: 250.72 +/- 16.87
+      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 CHANGED Viewed

@@ -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", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "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": false, "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 0x7eba50b4b1c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eba50b4b250>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eba50b4b2e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eba50b4b370>", "_build": "<function ActorCriticPolicy._build at 0x7eba50b4b400>", "forward": "<function ActorCriticPolicy.forward at 0x7eba50b4b490>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eba50b4b520>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eba50b4b5b0>", "_predict": "<function ActorCriticPolicy._predict at 0x7eba50b4b640>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eba50b4b6d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eba50b4b760>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eba50b4b7f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7eba5a628e00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1705324700087668662, "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:": "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": 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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caab5cf809ce7d8fc0df228f0f2e16d90428dcad31bad99d035788f5b4baa344
-size 148068

 version https://git-lfs.github.com/spec/v1
+oid sha256:36c928e4b13beb901ccc171c9a91e46811b58e8a9f8f1e58cef419aa5e767043
+size 148064

ppo-LunarLander-v2/data CHANGED Viewed

@@ -4,20 +4,20 @@
         ":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 0x7f038d23c4c0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f038d23c550>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f038d23c5e0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f038d23c670>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f038d23c700>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f038d23c790>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f038d23c820>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f038d23c8b0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f038d23c940>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f038d23c9d0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f038d23ca60>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f038d23caf0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f038d3e33c0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -26,12 +26,12 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1705301315155060306,
     "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'>",
@@ -45,7 +45,7 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",

         ":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 0x7eba50b4b1c0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eba50b4b250>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eba50b4b2e0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eba50b4b370>",
+        "_build": "<function ActorCriticPolicy._build at 0x7eba50b4b400>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7eba50b4b490>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eba50b4b520>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eba50b4b5b0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7eba50b4b640>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eba50b4b6d0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eba50b4b760>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eba50b4b7f0>",
         "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7eba5a628e00>"
     },
     "verbose": 1,
     "policy_kwargs": {},
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
+    "start_time": 1705324700087668662,
     "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'>",
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",

ppo-LunarLander-v2/policy.optimizer.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eec0753ad0fbda570500d38003817c3b356f714617890ed5568a3206112ba1e
 size 88362

 version https://git-lfs.github.com/spec/v1
+oid sha256:4d19b6a0842d645bca49686c9c2edfa3a812fd94a2ab52164e2da28bd20fc8de
 size 88362

ppo-LunarLander-v2/policy.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:491fd3d789ca531fce850092a6cb5ff99e6f9df2a848edd7954f979dd9e8d4e6
 size 43762

 version https://git-lfs.github.com/spec/v1
+oid sha256:5171c7291b7f706cd7950aff94f776c501b7a182af0ec58be61ea094efd2d24a
 size 43762

replay.mp4 CHANGED Viewed

Binary files a/replay.mp4 and b/replay.mp4 differ

results.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"mean_reward": ~~245~~.~~61088329999998~~, "std_reward": 22.~~190557108010843~~, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-~~15T07~~:22:21.~~886491~~"}


1	+ {"mean_reward": 250.71537249999997, "std_reward": 16.869271600464476, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-15T13:40:05.641341"}