Initial commit

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard 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 +1,67 @@
+---
+library_name: stable-baselines3
+tags:
+- BipedalWalker-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TQC
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 334.73 +/- 0.28
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: BipedalWalker-v3
+      type: BipedalWalker-v3
+---
+
+# **TQC** Agent playing **BipedalWalker-v3**
+This is a trained model of a **TQC** agent playing **BipedalWalker-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
+
+```
+# Download model and save it into the logs/ folder
+python -m utils.load_from_hub --algo tqc --env BipedalWalker-v3 -orga sb3 -f logs/
+python enjoy.py --algo tqc --env BipedalWalker-v3  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo tqc --env BipedalWalker-v3 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo tqc --env BipedalWalker-v3 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 256),
+             ('buffer_size', 300000),
+             ('ent_coef', 'auto'),
+             ('gamma', 0.98),
+             ('gradient_steps', 64),
+             ('learning_rate', 0.00073),
+             ('learning_starts', 10000),
+             ('n_timesteps', 500000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(log_std_init=-3, net_arch=[400, 300])'),
+             ('tau', 0.02),
+             ('train_freq', 64),
+             ('use_sde', True),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,59 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - tqc
+  - - env
+    - BipedalWalker-v3
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 10
+  - - eval_freq
+    - 10000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - rl-trained-agents/
+  - - log_interval
+    - -1
+  - - n_evaluations
+    - 20
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 10
+  - - num_threads
+    - -1
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 1977485241
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - true
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,27 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 256
+  - - buffer_size
+    - 300000
+  - - ent_coef
+    - auto
+  - - gamma
+    - 0.98
+  - - gradient_steps
+    - 64
+  - - learning_rate
+    - 0.00073
+  - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 500000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(log_std_init=-3, net_arch=[400, 300])
+  - - tau
+    - 0.02
+  - - train_freq
+    - 64
+  - - use_sde
+    - true

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8866aed36ecabcf56442b874800ece0dbf8a33177e3ed9db5579fa0fa447b4cc
+size 444608

results.json

@@ -0,0 +1 @@
+{"mean_reward": 334.7348148, "std_reward": 0.28109425008840366, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T21:20:50.614203"}

tqc-BipedalWalker-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a6116d8a395b7a04b4c1d3accba52ddb9ae7172e7a17ce7a81ada7bd510e6d1
+size 6098309

tqc-BipedalWalker-v3/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.1a8

tqc-BipedalWalker-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10befbd3b3a5f49a0e84bf3252de1f900ab29666bf0be7feb7071003f92dcfb9
+size 1065467

tqc-BipedalWalker-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd802dbf89613ed7ab343f4a2a574545e9a1ea26b40c613b7f18397ccbdac01
+size 2237085

tqc-BipedalWalker-v3/data

@@ -0,0 +1,123 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVKgAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMCVRRQ1BvbGljeZSTlC4=",
+        "__module__": "sb3_contrib.tqc.policies",
+        "__doc__": "\n    Policy class (with both actor and critic) for TQC.\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 use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the feature 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_quantiles: Number of quantiles for the critic.\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 TQCPolicy.__init__ at 0x7f216a90a710>",
+        "_build": "<function TQCPolicy._build at 0x7f216a90a7a0>",
+        "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7f216a90a830>",
+        "reset_noise": "<function TQCPolicy.reset_noise at 0x7f216a90a8c0>",
+        "make_actor": "<function TQCPolicy.make_actor at 0x7f216a90a950>",
+        "make_critic": "<function TQCPolicy.make_critic at 0x7f216a90a9e0>",
+        "forward": "<function TQCPolicy.forward at 0x7f216a90aa70>",
+        "_predict": "<function TQCPolicy._predict at 0x7f216a90ab00>",
+        "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7f216a90ab90>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f216a96a690>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "log_std_init": -3,
+        "net_arch": [
+            400,
+            300
+        ],
+        "use_sde": true
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gASVYwIAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMA2xvd5SMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlGgGjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxiFlGgKiUNgAACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/lHSUYowEaGlnaJRoEGgSSwCFlGgUh5RSlChLAUsYhZRoColDYAAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5R0lGKMDWJvdW5kZWRfYmVsb3eUaBBoEksAhZRoFIeUUpQoSwFLGIWUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGKJQxgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUdJRijA1ib3VuZGVkX2Fib3ZllGgQaBJLAIWUaBSHlFKUKEsBSxiFlGgoiUMYAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlHSUYowKX25wX3JhbmRvbZROjAZfc2hhcGWUSxiFlHViLg==",
+        "dtype": "float32",
+        "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,
+        "_shape": [
+            24
+        ]
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "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)",
+        "_shape": [
+            4
+        ]
+    },
+    "n_envs": 1,
+    "num_timesteps": 500032,
+    "_total_timesteps": 500000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1614710447.130888,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gASV2QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxVL3ZvbHVtZS9VU0VSU1RPUkUvcmFmZl9hbi9wcm9qZWN0cy90b3JjaHktYmFzZWxpbmVzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS3xDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMVS92b2x1bWUvVVNFUlNUT1JFL3JhZmZfYW4vcHJvamVjdHMvdG9yY2h5LWJhc2VsaW5lcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoIH2UfZQoaBdoDowMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBiMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP0frrxAjY7KFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
+    },
+    "_last_obs": null,
+    "_last_episode_starts": null,
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASV6gAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLGIaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUNg+JE4Pm9RjLzXTdg9L0yovbP9jD+BklQ/eGQgvwAAAAAAAAAAlWS+vkVP4D0Qfq89i0NGvgAAAAA64MQ+mRzHPoUUzj5zpNo+V4ruPgaJBj8TXB4/Q9ZFPwAAgD8AAIA/lHSUYi4="
+    },
+    "_episode_num": 909,
+    "use_sde": true,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -6.4000000000064e-05,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 490048,
+    "buffer_size": 1,
+    "batch_size": 256,
+    "learning_starts": 10000,
+    "tau": 0.02,
+    "gamma": 0.98,
+    "gradient_steps": 64,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__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:\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    :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 0x7f216b0e4b90>",
+        "add": "<function ReplayBuffer.add at 0x7f216b0e4c20>",
+        "sample": "<function ReplayBuffer.sample at 0x7f216ac4b7a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f216ac4b830>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f216b13b5d0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLQGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -4.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "top_quantiles_to_drop_per_net": 2,
+    "_last_dones": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQCUdJRiLg=="
+    },
+    "remove_time_limit_termination": false
+}

tqc-BipedalWalker-v3/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52cf453030022fa54970758c16870b3b5e11dc92142f07fadeecf879402629fb
+size 1255

tqc-BipedalWalker-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:594355e97c1a3b510bfc6d88d956cc2b2214dd6d1d2678f9d56cf13887d918ee
+size 2771784

tqc-BipedalWalker-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0d967b8c3cae279f44b5586c365546a35335f3198068fcab1f9e964b91862a9
+size 747

tqc-BipedalWalker-v3/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.13.0-44-generic-x86_64-with-debian-bullseye-sid #49~20.04.1-Ubuntu SMP Wed May 18 18:44:28 UTC 2022
+Python: 3.7.10
+Stable-Baselines3: 1.5.1a8
+PyTorch: 1.11.0
+GPU Enabled: True
+Numpy: 1.21.2
+Gym: 0.21.0

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9da614673c2bc33cb9be50e4ea1bc7c0b5d3591d54ef3953b7647a098b530940
+size 35331