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:
+- MountainCarContinuous-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TQC
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 76.40 +/- 38.49
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: MountainCarContinuous-v0
+      type: MountainCarContinuous-v0
+---
+
+# **TQC** Agent playing **MountainCarContinuous-v0**
+This is a trained model of a **TQC** agent playing **MountainCarContinuous-v0**
+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 MountainCarContinuous-v0 -orga sb3 -f logs/
+python enjoy.py --algo tqc --env MountainCarContinuous-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo tqc --env MountainCarContinuous-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo tqc --env MountainCarContinuous-v0 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 512),
+             ('buffer_size', 50000),
+             ('ent_coef', 0.1),
+             ('gamma', 0.9999),
+             ('gradient_steps', 32),
+             ('learning_rate', 0.0003),
+             ('learning_starts', 0),
+             ('n_timesteps', 50000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(log_std_init=-3.67, net_arch=[64, 64])'),
+             ('tau', 0.01),
+             ('train_freq', 32),
+             ('use_sde', True),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,59 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - tqc
+  - - env
+    - MountainCarContinuous-v0
+  - - 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
+    - 1954841141
+  - - 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
+    - 512
+  - - buffer_size
+    - 50000
+  - - ent_coef
+    - 0.1
+  - - gamma
+    - 0.9999
+  - - gradient_steps
+    - 32
+  - - learning_rate
+    - 0.0003
+  - - learning_starts
+    - 0
+  - - n_timesteps
+    - 50000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(log_std_init=-3.67, net_arch=[64, 64])
+  - - tau
+    - 0.01
+  - - train_freq
+    - 32
+  - - 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:e6c2a92b42b84035cb3ac47c85a484f54ffa1fd2f0e1d6730b8c5349b9b53910
+size 213406

results.json

@@ -0,0 +1 @@
+{"mean_reward": 76.3968701, "std_reward": 38.48772138614096, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T22:00:15.398974"}

tqc-MountainCarContinuous-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9cb279639e9c952dcfeed85a2b4b4af602aff4876ffe6f6f26f5328ce87734d
+size 287747

tqc-MountainCarContinuous-v0/_stable_baselines3_version

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

tqc-MountainCarContinuous-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e187ff10319596cd640eb0dc208537b5ba447b7016b142a20f2a5e0384a105d9
+size 39675

tqc-MountainCarContinuous-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5488beff2bb6559710ce0494cd8050951438ded8bfe24f3b7b04f2f0b536418
+size 102941

tqc-MountainCarContinuous-v0/data

@@ -0,0 +1,125 @@
+{
+    "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 0x7f86c2354710>",
+        "_build": "<function TQCPolicy._build at 0x7f86c23547a0>",
+        "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7f86c2354830>",
+        "reset_noise": "<function TQCPolicy.reset_noise at 0x7f86c23548c0>",
+        "make_actor": "<function TQCPolicy.make_actor at 0x7f86c2354950>",
+        "make_critic": "<function TQCPolicy.make_critic at 0x7f86c23549e0>",
+        "forward": "<function TQCPolicy.forward at 0x7f86c2354a70>",
+        "_predict": "<function TQCPolicy._predict at 0x7f86c2354b00>",
+        "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7f86c2354b90>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f86c23b4690>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "log_std_init": -3.67,
+        "net_arch": [
+            64,
+            64
+        ],
+        "use_sde": true
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "low": "[-1.2  -0.07]",
+        "high": "[0.6  0.07]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_np_random": null,
+        "_shape": [
+            2
+        ]
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "low": "[-1.]",
+        "high": "[1.]",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_np_random": "RandomState(MT19937)",
+        "_shape": [
+            1
+        ]
+    },
+    "n_envs": 1,
+    "num_timesteps": 50016,
+    "_total_timesteps": 50000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1614621348.7207866,
+    "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:": "gASVkgAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLAoaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUMIgMWXv/wknTuUdJRiLg=="
+    },
+    "_episode_num": 297,
+    "use_sde": true,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.000320000000000098,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 50016,
+    "buffer_size": 1,
+    "batch_size": 512,
+    "learning_starts": 0,
+    "tau": 0.01,
+    "gamma": 0.9999,
+    "gradient_steps": 32,
+    "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 0x7f86c2b2eb90>",
+        "add": "<function ReplayBuffer.add at 0x7f86c2b2ec20>",
+        "sample": "<function ReplayBuffer.sample at 0x7f86c26957a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f86c2695830>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f86c2b865d0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLIGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -1.0,
+    "log_ent_coef": null,
+    "ent_coef": 0.1,
+    "target_update_interval": 1,
+    "ent_coef_optimizer": null,
+    "top_quantiles_to_drop_per_net": 2,
+    "_last_dones": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQCUdJRiLg=="
+    },
+    "remove_time_limit_termination": false
+}

tqc-MountainCarContinuous-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8509b9a7bc1dc696b3723cc67a8560f1609dcaeec809911db3e953e8a8f1aad4
+size 125000

tqc-MountainCarContinuous-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39440af5158e3fb47ecc525e9d329ecbd7c856bf70fd565c749cc2c45263e188
+size 747

tqc-MountainCarContinuous-v0/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:d5f7902c1c8b65253bbf530f563d0229e1ef54389b048da27ffb708dda660d02
+size 9653