Initial commit

.gitattributes

@@ -32,3 +32,4 @@ 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
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,77 @@
+---
+library_name: stable-baselines3
+tags:
+- BipedalWalkerHardcore-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TD3
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: BipedalWalkerHardcore-v3
+      type: BipedalWalkerHardcore-v3
+    metrics:
+    - type: mean_reward
+      value: -24.80 +/- 3.78
+      name: mean_reward
+      verified: false
+---
+
+# **TD3** Agent playing **BipedalWalkerHardcore-v3**
+This is a trained model of a **TD3** agent playing **BipedalWalkerHardcore-v3**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
+and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
+
+The RL Zoo is a training framework for Stable Baselines3
+reinforcement learning agents,
+with hyperparameter optimization and pre-trained agents included.
+
+## Usage (with SB3 RL Zoo)
+
+RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
+SB3: https://github.com/DLR-RM/stable-baselines3<br/>
+SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
+
+Install the RL Zoo (with SB3 and SB3-Contrib):
+```bash
+pip install rl_zoo3
+```
+
+```
+# Download model and save it into the logs/ folder
+python -m rl_zoo3.load_from_hub --algo td3 --env BipedalWalkerHardcore-v3 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo td3 --env BipedalWalkerHardcore-v3  -f logs/
+```
+
+If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
+```
+python -m rl_zoo3.load_from_hub --algo td3 --env BipedalWalkerHardcore-v3 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo td3 --env BipedalWalkerHardcore-v3  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo td3 --env BipedalWalkerHardcore-v3 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo td3 --env BipedalWalkerHardcore-v3 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 256),
+             ('buffer_size', 1000000),
+             ('gamma', 0.99),
+             ('learning_rate', 'lin_7e-4'),
+             ('learning_starts', 10000),
+             ('n_timesteps', 10000000.0),
+             ('noise_std', 0.1),
+             ('noise_type', 'normal'),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(net_arch=[400, 300])'),
+             ('train_freq', 1),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - td3
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - BipedalWalkerHardcore-v3
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 1
+  - - n_evaluations
+    - null
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 500
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - -1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 3214139235
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/BipedalWalkerHardcore-v3__td3__3214139235__1672169167
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - openrlbenchmark
+  - - wandb_project_name
+    - sb3
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,23 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 256
+  - - buffer_size
+    - 1000000
+  - - gamma
+    - 0.99
+  - - learning_rate
+    - lin_7e-4
+  - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 10000000.0
+  - - noise_std
+    - 0.1
+  - - noise_type
+    - normal
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(net_arch=[400, 300])
+  - - train_freq
+    - 1

env_kwargs.yml

@@ -0,0 +1 @@
+{}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbc74a770a0a25ccf24c6cac78c4f404371287b2762dadf09c745adcc2daa6a7
+size 99736

results.json

@@ -0,0 +1 @@
+{"mean_reward": -24.8020791, "std_reward": 3.7823493281860796, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T16:26:13.705394"}

td3-BipedalWalkerHardcore-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35bcc879fc2e1a113d5663afc41b444e5e4432d318b2c56483e69e148f1b76b6
+size 6383296

td3-BipedalWalkerHardcore-v3/_stable_baselines3_version

@@ -0,0 +1 @@
+1.8.0a6

td3-BipedalWalkerHardcore-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6f52da73307fea3a06911cd5ea5ab767514d4b1e52ad1344847dd8479a76e0
+size 1056943

td3-BipedalWalkerHardcore-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbceca2fd2a34474c68fb39103de28399f46d8cc49f00f1726aff3a1f0d832a9
+size 2124601

td3-BipedalWalkerHardcore-v3/data

@@ -0,0 +1,126 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnRkMy5wb2xpY2llc5SMCVREM1BvbGljeZSTlC4=",
+        "__module__": "stable_baselines3.td3.policies",
+        "__doc__": "\n    Policy class (with both actor and critic) for TD3.\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 features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\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    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ",
+        "__init__": "<function TD3Policy.__init__ at 0x7f14b43ed940>",
+        "_build": "<function TD3Policy._build at 0x7f14b43ed9d0>",
+        "_get_constructor_parameters": "<function TD3Policy._get_constructor_parameters at 0x7f14b43eda60>",
+        "make_actor": "<function TD3Policy.make_actor at 0x7f14b43edaf0>",
+        "make_critic": "<function TD3Policy.make_critic at 0x7f14b43edb80>",
+        "forward": "<function TD3Policy.forward at 0x7f14b43edc10>",
+        "_predict": "<function TD3Policy._predict at 0x7f14b43edca0>",
+        "set_training_mode": "<function TD3Policy.set_training_mode at 0x7f14b43edd30>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f14b43f16c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            400,
+            300
+        ]
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            24
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            4
+        ],
+        "low": "[-1. -1. -1. -1.]",
+        "high": "[1. 1. 1. 1.]",
+        "bounded_below": "[ True  True  True  True]",
+        "bounded_above": "[ True  True  True  True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 10000000,
+    "_total_timesteps": 10000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": {
+        ":type:": "<class 'stable_baselines3.common.noise.NormalActionNoise'>",
+        ":serialized:": "gAWVGgEAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5ub2lzZZSMEU5vcm1hbEFjdGlvbk5vaXNllJOUKYGUfZQojANfbXWUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLBIWUjAFDlHSUUpSMBl9zaWdtYZRoCCiWIAAAAAAAAACamZmZmZm5P5qZmZmZmbk/mpmZmZmZuT+amZmZmZm5P5RoD0sEhZRoE3SUUpR1Yi4=",
+        "_mu": "[0. 0. 0. 0.]",
+        "_sigma": "[0.1 0.1 0.1 0.1]"
+    },
+    "start_time": 1672169169425681435,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/BipedalWalkerHardcore-v3__td3__3214139235__1672169167/BipedalWalkerHardcore-v3",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV1QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZgAAAAAAAAAFB9gL0jJZC7A8QGPHQI8buQxFW/AABytMhtpT37/38/AAAAANFXjD9whxk9oBtrPwAAyLMAAIA/YKRJPpruSz63EVM+gO9fPrZQdD7Qyok+9gEAP9wx5z48Hgs//slnP5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsYhpSMAUOUdJRSlC4="
+    },
+    "_episode_num": 5671,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 9990000,
+    "buffer_size": 1,
+    "batch_size": 256,
+    "learning_starts": 10000,
+    "tau": 0.005,
+    "gamma": 0.99,
+    "gradient_steps": -1,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__module__": "stable_baselines3.common.buffers",
+        "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7f14b43ea430>",
+        "add": "<function ReplayBuffer.add at 0x7f14b43ea4c0>",
+        "sample": "<function ReplayBuffer.sample at 0x7f14b43ea550>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f14b43ea5e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f14b43e4500>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "policy_delay": 2,
+    "target_noise_clip": 0.5,
+    "target_policy_noise": 0.2,
+    "actor_batch_norm_stats": [],
+    "critic_batch_norm_stats": [],
+    "actor_batch_norm_stats_target": [],
+    "critic_batch_norm_stats_target": []
+}

td3-BipedalWalkerHardcore-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b63c1952d9d35ba0840b042038b80cd4216211a9c39a37272f17227f9038d71b
+size 3179321

td3-BipedalWalkerHardcore-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

td3-BipedalWalkerHardcore-v3/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
+- Python: 3.9.12
+- Stable-Baselines3: 1.8.0a6
+- PyTorch: 1.13.1+cu117
+- GPU Enabled: True
+- Numpy: 1.24.1
+- Gym: 0.21.0

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c6dfac13f2a78d3e6676c946279768db90c28097654a5db025cde0c826efc04
+size 202738