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 +1,71 @@
+---
+library_name: stable-baselines3
+tags:
+- Walker2d-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TD3
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Walker2d-v3
+      type: Walker2d-v3
+    metrics:
+    - type: mean_reward
+      value: 4062.85 +/- 23.42
+      name: mean_reward
+      verified: false
+---
+
+# **TD3** Agent playing **Walker2d-v3**
+This is a trained model of a **TD3** agent playing **Walker2d-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 Walker2d-v3 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo td3 --env Walker2d-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 Walker2d-v3 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo td3 --env Walker2d-v3  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo td3 --env Walker2d-v3 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo td3 --env Walker2d-v3 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('learning_starts', 10000),
+             ('n_timesteps', 1000000.0),
+             ('noise_std', 0.1),
+             ('noise_type', 'normal'),
+             ('policy', 'MlpPolicy'),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,83 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - td3
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - Walker2d-v3
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 5
+  - - 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
+    - 2777684055
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/Walker2d-v3__td3__2777684055__1676687322
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - openrlbenchmark
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,11 @@
+!!python/object/apply:collections.OrderedDict
+- - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 1000000.0
+  - - noise_std
+    - 0.1
+  - - noise_type
+    - normal
+  - - policy
+    - MlpPolicy

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efd428853264aea2bf07c2b3f8f9200c4c6bd0def82558a39f11ddf4e5a0c058
+size 1265888

results.json

@@ -0,0 +1 @@
+{"mean_reward": 4062.8485315000007, "std_reward": 23.41861510059941, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T17:43:55.784896"}

td3-Walker2d-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b891d4238aaada7f92f00c8231b0da4728f35af187eee987ee2cf846c2767c7
+size 6282626

td3-Walker2d-v3/_stable_baselines3_version

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

td3-Walker2d-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf21109ae39159ba8f88bef63893e750c29a87fd665909986426d33155fd5e3f
+size 1039279

td3-Walker2d-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:104e9d6ac28826a20f7ab557971d4cf0bf56b4cbe990c05f58d4347106138648
+size 2092601

td3-Walker2d-v3/data

@@ -0,0 +1,118 @@
+{
+    "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 0x7f33ac070af0>",
+        "_build": "<function TD3Policy._build at 0x7f33ac070b80>",
+        "_get_constructor_parameters": "<function TD3Policy._get_constructor_parameters at 0x7f33ac070c10>",
+        "make_actor": "<function TD3Policy.make_actor at 0x7f33ac070ca0>",
+        "make_critic": "<function TD3Policy.make_critic at 0x7f33ac070d30>",
+        "forward": "<function TD3Policy.forward at 0x7f33ac070dc0>",
+        "_predict": "<function TD3Policy._predict at 0x7f33ac070e50>",
+        "set_training_mode": "<function TD3Policy.set_training_mode at 0x7f33ac070ee0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f33ac075580>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVgQIAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLEYWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWiAAAAAAAAAAAAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/AAAAAAAA8P8AAAAAAADw/wAAAAAAAPD/lGgKSxGFlIwBQ5R0lFKUjARoaWdolGgSKJaIAAAAAAAAAAAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H8AAAAAAADwfwAAAAAAAPB/AAAAAAAA8H+UaApLEYWUaBV0lFKUjA1ib3VuZGVkX2JlbG93lGgSKJYRAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlGgHjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxGFlGgVdJRSlIwNYm91bmRlZF9hYm92ZZRoEiiWEQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJRoIUsRhZRoFXSUUpSMCl9ucF9yYW5kb22UTnViLg==",
+        "dtype": "float64",
+        "_shape": [
+            17
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf inf inf inf 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]",
+        "bounded_above": "[False False False False False False False False False False False False\n False False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            6
+        ],
+        "low": "[-1. -1. -1. -1. -1. -1.]",
+        "high": "[1. 1. 1. 1. 1. 1.]",
+        "bounded_below": "[ True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 1000423,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": {
+        ":type:": "<class 'stable_baselines3.common.noise.NormalActionNoise'>",
+        ":serialized:": "gAWVOgEAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5ub2lzZZSMEU5vcm1hbEFjdGlvbk5vaXNllJOUKYGUfZQojANfbXWUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWMAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwaFlIwBQ5R0lFKUjAZfc2lnbWGUaAgoljAAAAAAAAAAmpmZmZmZuT+amZmZmZm5P5qZmZmZmbk/mpmZmZmZuT+amZmZmZm5P5qZmZmZmbk/lGgPSwaFlGgTdJRSlHViLg==",
+        "_mu": "[0. 0. 0. 0. 0. 0.]",
+        "_sigma": "[0.1 0.1 0.1 0.1 0.1 0.1]"
+    },
+    "start_time": 1676687324710310360,
+    "learning_rate": 0.001,
+    "tensorboard_log": "runs/Walker2d-v3__td3__2777684055__1676687322/Walker2d-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:": "gAWV/QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaIAAAAAAAAAB3qFhESKfM/VAqpenm7wD9yDvN5y06hP0KEf/8IF5U/NK8uMkLL6T+ikBgo4VLQv9OZmeSuGJA/3eFFf96x6T98BxwrjRcLQAl086wrtvW/uqMVckcL0b89iRCqGCXMvxoQDYXyzPC/iARKGSNhEsAozTbYfn2lvx4YgSFQwo0/LvvdSVYNnb+UjAVudW1weZSMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLEYaUjAFDlHSUUpQu"
+    },
+    "_episode_num": 2751,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.0004230000000000622,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 990423,
+    "buffer_size": 1,
+    "batch_size": 100,
+    "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 0x7f33ac06e5e0>",
+        "add": "<function ReplayBuffer.add at 0x7f33ac06e670>",
+        "sample": "<function ReplayBuffer.sample at 0x7f33ac06e700>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f33ac06e790>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f33ac0683c0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVZAAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMB2VwaXNvZGWUhZRSlIaUgZQu"
+    },
+    "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-Walker2d-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1c19f02071abd0fb289f9a31773edf190527a2cd947270c2b6bab4ddbe80a1
+size 3129721

td3-Walker2d-v3/pytorch_variables.pth

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

td3-Walker2d-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 sha256:65be7623618d8ec044027474987e6719ce64b6b48099eb3c81a23cc72f2eafd3
+size 87611