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 +1,57 @@
+---
+library_name: stable-baselines3
+tags:
+- Pendulum-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TQC
+  results:
+  - metrics:
+    - type: mean_reward
+      value: -171.32 +/- 96.54
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pendulum-v1
+      type: Pendulum-v1
+---
+
+# **TQC** Agent playing **Pendulum-v1**
+This is a trained model of a **TQC** agent playing **Pendulum-v1**
+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 Pendulum-v1 -orga sb3 -f logs/
+python enjoy.py --algo tqc --env Pendulum-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo tqc --env Pendulum-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo tqc --env Pendulum-v1 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('learning_rate', 0.001),
+             ('n_timesteps', 20000),
+             ('policy', 'MlpPolicy'),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,73 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - tqc
+  - - device
+    - auto
+  - - env
+    - Pendulum-v1
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 5000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs/
+  - - log_interval
+    - -1
+  - - n_eval_envs
+    - 1
+  - - 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
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 2347514426
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - track
+    - false
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - sb3

config.yml

@@ -0,0 +1,7 @@
+!!python/object/apply:collections.OrderedDict
+- - - learning_rate
+    - 0.001
+  - - n_timesteps
+    - 20000
+  - - policy
+    - MlpPolicy

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b62acf4a992241ae9af3177aafad9dad123122ca29943b8023f4bb00f579c8d
+size 230244

results.json

@@ -0,0 +1 @@
+{"mean_reward": -171.31813649999998, "std_reward": 96.53819756951812, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-22T22:35:48.222434"}

tqc-Pendulum-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b393e819b74e7060007fa84c5b8eab3851debb3368591d66478e9d199f6c2be3
+size 3203058

tqc-Pendulum-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.1a6

tqc-Pendulum-v1/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3667db381eb9632de7c33ec91daa54cb4f534745d0b85aa578541942b0d6feb
+size 542837

tqc-Pendulum-v1/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b62d6b356d627051d90d7f20a6e92a986fb3bf2949f124e4e89f31b21668e9c
+size 1182045

tqc-Pendulum-v1/data

@@ -0,0 +1,116 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVKgAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMCVRRQ1BvbGljeZSTlC4=",
+        "__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 0x7fb312384f80>",
+        "_build": "<function TQCPolicy._build at 0x7fb312388050>",
+        "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7fb3123880e0>",
+        "reset_noise": "<function TQCPolicy.reset_noise at 0x7fb312388170>",
+        "make_actor": "<function TQCPolicy.make_actor at 0x7fb312388200>",
+        "make_critic": "<function TQCPolicy.make_critic at 0x7fb312388290>",
+        "forward": "<function TQCPolicy.forward at 0x7fb312388320>",
+        "_predict": "<function TQCPolicy._predict at 0x7fb3123883b0>",
+        "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7fb312388440>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fb3123e54b0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "use_sde": false
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            3
+        ],
+        "low": "[-1. -1. -8.]",
+        "high": "[1. 1. 8.]",
+        "bounded_below": "[ True  True  True]",
+        "bounded_above": "[ True  True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            1
+        ],
+        "low": "[-2.]",
+        "high": "[2.]",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 20000,
+    "_total_timesteps": 20000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1653251033.580683,
+    "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": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAAAYefz8/7am9j6C8vZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsDhpSMAUOUdJRSlC4="
+    },
+    "_episode_num": 100,
+    "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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 19900,
+    "buffer_size": 1,
+    "batch_size": 256,
+    "learning_starts": 100,
+    "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:\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 0x7fb312b5bcb0>",
+        "add": "<function ReplayBuffer.add at 0x7fb312b5bd40>",
+        "sample": "<function ReplayBuffer.sample at 0x7fb312b51440>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fb312b514d0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fb312bbb3f0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -1.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "top_quantiles_to_drop_per_net": 2
+}

tqc-Pendulum-v1/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a6e137feba619dae41b557e8d62ce9aee3fd3c8533b414040c5f85af493e077
+size 1191

tqc-Pendulum-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a212e5de577f9b72c58b1b8d0720c99b4e2f68033eda2a3faba93ea915a0626e
+size 1455685

tqc-Pendulum-v1/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ce80cb691e906c9e7770bffead06beda0512716cbcbc9bacdf69bf1b00a3f42
+size 747

tqc-Pendulum-v1/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.4.0-110-generic-x86_64-with-debian-bullseye-sid #124-Ubuntu SMP Thu Apr 14 19:46:19 UTC 2022
+Python: 3.7.12
+Stable-Baselines3: 1.5.1a6
+PyTorch: 1.11.0+cpu
+GPU Enabled: False
+Numpy: 1.21.6
+Gym: 0.21.0

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5e12368757ee160fad707977c2c2a88a24f92b18f13823e17c82d994d2bf071
+size 4177