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 +1,58 @@
+---
+library_name: stable-baselines3
+tags:
+- Walker2d-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TQC
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 4489.57 +/- 43.87
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Walker2d-v3
+      type: Walker2d-v3
+---
+
+# **TQC** Agent playing **Walker2d-v3**
+This is a trained model of a **TQC** 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
+
+```
+# Download model and save it into the logs/ folder
+python -m utils.load_from_hub --algo tqc --env Walker2d-v3 -orga sb3 -f logs/
+python enjoy.py --algo tqc --env Walker2d-v3  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo tqc --env Walker2d-v3 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo tqc --env Walker2d-v3 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('learning_starts', 10000),
+             ('n_timesteps', 1000000.0),
+             ('policy', 'MlpPolicy'),
+             ('use_sde', False),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,65 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - tqc
+  - - env
+    - Walker2d-v3
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 10000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - use_sde: false
+  - - log_folder
+    - logs/
+  - - log_interval
+    - 10
+  - - n_eval_envs
+    - 5
+  - - n_evaluations
+    - 20
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - 1000000
+  - - n_trials
+    - 10
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - 2
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 594371
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - true
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,9 @@
+!!python/object/apply:collections.OrderedDict
+- - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 1000000.0
+  - - policy
+    - MlpPolicy
+  - - use_sde
+    - false

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed2e02926a8e0437ce213d3de7caa622e198ead6bab243f140761cdbfaee7fee
+size 1362888

results.json

@@ -0,0 +1 @@
+{"mean_reward": 4489.5663072, "std_reward": 43.87114297624282, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T20:51:17.699776"}

tqc-Walker2d-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:194cd7fe5f86ae6bca03aa60037bd7eca1da608990e9dd1dc1ad1fe3310288c1
+size 3433739

tqc-Walker2d-v3/_stable_baselines3_version

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

tqc-Walker2d-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64137940b4870bfb17ce87313511992d8c259582040cdfa6a3bfaeb15a02c3cd
+size 592181

tqc-Walker2d-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:742f4e302afdbcca7dac88ddd9113572a54acaad541403ef991a572dcab47c92
+size 1260189

tqc-Walker2d-v3/data

@@ -0,0 +1,114 @@
+{
+    "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 0x7ff3b0770710>",
+        "_build": "<function TQCPolicy._build at 0x7ff3b07707a0>",
+        "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7ff3b0770830>",
+        "reset_noise": "<function TQCPolicy.reset_noise at 0x7ff3b07708c0>",
+        "make_actor": "<function TQCPolicy.make_actor at 0x7ff3b0770950>",
+        "make_critic": "<function TQCPolicy.make_critic at 0x7ff3b07709e0>",
+        "forward": "<function TQCPolicy.forward at 0x7ff3b0770a70>",
+        "_predict": "<function TQCPolicy._predict at 0x7ff3b0770b00>",
+        "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7ff3b0770b90>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7ff3b07d0690>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "use_sde": false
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "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,
+        "_shape": [
+            17
+        ]
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "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)",
+        "_shape": [
+            6
+        ]
+    },
+    "n_envs": 1,
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1635497714.8084626,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQGUdJRiLg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVEgEAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLEYaUaAOMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUOIq7gnGkEQ9D/sk0loSFXOP49GY1mkYKS/MYaUfK0/17/UkuTHmz7Xvy3Zx9OZrI0/YjZEcyjC9L/mkM2f1THrP7044dvEQRJAENYXvda9AED8trJrO5PjP6C/p2BslQfAVTlLO1r8EEAAAAAAAAAkwLFTQWPx7PE/N4I6X9VbEUApuh9Wiojwv5R0lGIu"
+    },
+    "_episode_num": 2528,
+    "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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 990000,
+    "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:": "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 0x7ff3b0f4ab90>",
+        "add": "<function ReplayBuffer.add at 0x7ff3b0f4ac20>",
+        "sample": "<function ReplayBuffer.sample at 0x7ff3b0ab17a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7ff3b0ab1830>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7ff3b0fa15d0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -6.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "top_quantiles_to_drop_per_net": 2,
+    "remove_time_limit_termination": false
+}

tqc-Walker2d-v3/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a4035353e00d994e194698ea8ba1a1d94607d469869c686451541b3931f48cb
+size 1255

tqc-Walker2d-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3949a5bcac1956b8053506830b69e25004b8f65a861072cd77de483db8a48e39
+size 1558533

tqc-Walker2d-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1bdd531dd6516f02269c965d19b053d0b26644d6966ba6e23c2e83020f5a4c4
+size 747

tqc-Walker2d-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:f28db8fa083ab5fda4fab94b66baae393de6cea5bfb0b582deb58050463bc75c
+size 102813