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 +1,66 @@
+---
+library_name: stable-baselines3
+tags:
+- BipedalWalkerHardcore-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TQC
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 208.05 +/- 121.38
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: BipedalWalkerHardcore-v3
+      type: BipedalWalkerHardcore-v3
+---
+
+# **TQC** Agent playing **BipedalWalkerHardcore-v3**
+This is a trained model of a **TQC** 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
+
+```
+# Download model and save it into the logs/ folder
+python -m utils.load_from_hub --algo tqc --env BipedalWalkerHardcore-v3 -orga sb3 -f logs/
+python enjoy.py --algo tqc --env BipedalWalkerHardcore-v3  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo tqc --env BipedalWalkerHardcore-v3 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo tqc --env BipedalWalkerHardcore-v3 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 256),
+             ('buffer_size', 1000000),
+             ('ent_coef', 'auto'),
+             ('gamma', 0.99),
+             ('gradient_steps', 1),
+             ('learning_rate', 'lin_7.3e-4'),
+             ('learning_starts', 10000),
+             ('n_timesteps', 2000000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(net_arch=[400, 300])'),
+             ('tau', 0.01),
+             ('train_freq', 1),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,59 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - tqc
+  - - env
+    - BipedalWalkerHardcore-v3
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 10
+  - - eval_freq
+    - 50000
+  - - 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
+    - 3024001206
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,25 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 256
+  - - buffer_size
+    - 1000000
+  - - ent_coef
+    - auto
+  - - gamma
+    - 0.99
+  - - gradient_steps
+    - 1
+  - - learning_rate
+    - lin_7.3e-4
+  - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 2000000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(net_arch=[400, 300])
+  - - tau
+    - 0.01
+  - - train_freq
+    - 1

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:893e9e1eec2af8806b49b4233a876ea963923129d982526dae6220aec78eabf1
+size 476618

results.json

@@ -0,0 +1 @@
+{"mean_reward": 208.04946040000004, "std_reward": 121.38381506379628, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T21:40:05.221843"}

tqc-BipedalWalkerHardcore-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c2bcabe1e1aa1e2abdaaaa9cd3e00ec2d69b1511e221921d3053ca80aa55e9b
+size 6099713

tqc-BipedalWalkerHardcore-v3/_stable_baselines3_version

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

tqc-BipedalWalkerHardcore-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac2578d8c68950424cbc90bbdc68cb1ced97d97dbfac53268ccf081e2cd6510a
+size 1066037

tqc-BipedalWalkerHardcore-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63ad130338dea357bb15311d03492d3cc7396a4e4148177d6a5d21167f350d08
+size 2237085

tqc-BipedalWalkerHardcore-v3/data

@@ -0,0 +1,122 @@
+{
+    "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 0x7f42467ff710>",
+        "_build": "<function TQCPolicy._build at 0x7f42467ff7a0>",
+        "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7f42467ff830>",
+        "reset_noise": "<function TQCPolicy.reset_noise at 0x7f42467ff8c0>",
+        "make_actor": "<function TQCPolicy.make_actor at 0x7f42467ff950>",
+        "make_critic": "<function TQCPolicy.make_critic at 0x7f42467ff9e0>",
+        "forward": "<function TQCPolicy.forward at 0x7f42467ffa70>",
+        "_predict": "<function TQCPolicy._predict at 0x7f42467ffb00>",
+        "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7f42467ffb90>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f42467f5690>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            400,
+            300
+        ],
+        "use_sde": false
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "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": 2000000,
+    "_total_timesteps": 2000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1614945894.3727493,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": null,
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASV6gAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLGIaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUNgDxGLPUudAz1oPx4/UtBIvTuExD4hCIC/+ENavpUMpD4AAIA/nRpWP1Cdx776aj0/6/9/PwAAAAD7PvE+VvzzPk+G/D6C9QU/MRosP84cPj8huFc/AACAPwAAgD8AAIA/lHSUYi4="
+    },
+    "_episode_num": 1852,
+    "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": 1990000,
+    "buffer_size": 1,
+    "batch_size": 256,
+    "learning_starts": 10000,
+    "tau": 0.01,
+    "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 0x7f4246fd9b90>",
+        "add": "<function ReplayBuffer.add at 0x7f4246fd9c20>",
+        "sample": "<function ReplayBuffer.sample at 0x7f4246b407a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f4246b40830>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f42470315d0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "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-BipedalWalkerHardcore-v3/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ea25e1d1eeb57a7adaf017a536cf1c9ed89204ea6577ead9429d94fa68f34ac
+size 1255

tqc-BipedalWalkerHardcore-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b176457dc78fb1448fdf61fd37d5763c0a13fcebbaec289e10b4319743ae988a
+size 2772101

tqc-BipedalWalkerHardcore-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66268f5e374c166d9491d8dfac783afa4002b53dcb9531a243274a2585caf116
+size 747

tqc-BipedalWalkerHardcore-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:db65027e20a49be71aebf3413c75292cab138e31890dbdf006aea711fef9e4e1
+size 61039