Initial commit

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst 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 +1,69 @@
+---
+library_name: stable-baselines3
+tags:
+- Pendulum-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TQC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pendulum-v1
+      type: Pendulum-v1
+    metrics:
+    - type: mean_reward
+      value: -170.67 +/- 96.58
+      name: mean_reward
+      verified: false
+---
+
+# **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
+
+Install the RL Zoo (with SB3 and SB3-Contrib):
+```bash
+pip install rl_zoo3
+```
+
+```
+# Download model and save it into the logs/ folder
+python -m rl_zoo3.load_from_hub --algo tqc --env Pendulum-v1 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo tqc --env Pendulum-v1  -f logs/
+```
+
+If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
+```
+python -m rl_zoo3.load_from_hub --algo tqc --env Pendulum-v1 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo tqc --env Pendulum-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo tqc --env Pendulum-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo tqc --env Pendulum-v1 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('learning_rate', 0.001),
+             ('n_timesteps', 20000),
+             ('policy', 'MlpPolicy'),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,79 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - tqc
+  - - device
+    - auto
+  - - env
+    - Pendulum-v1
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 5
+  - - 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
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 2735755449
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/Pendulum-v1__tqc__2735755449__1670944977
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - openrlbenchmark
+  - - wandb_project_name
+    - sb3
+  - - yaml_file
+    - null

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:c4ee7630ce46f9005632e7fda471f483043dad76399530e7d36faac65e6317a3
+size 122943

results.json

@@ -0,0 +1 @@
+{"mean_reward": -170.66704080000002, "std_reward": 96.5799652176509, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T16:52:54.169740"}

tqc-Pendulum-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27c24a179ee2354f35fde04f08bc850e68debcde4bc5e96dafbe8db9e06939a5
+size 3209842

tqc-Pendulum-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+1.8.0a6

tqc-Pendulum-v1/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:681908c3e10869ece58554fe33f5fa9a57826aaf5b0a4de8041e8f1fc50017ed
+size 545181

tqc-Pendulum-v1/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b7ae04384c93d51f7870ba1b7b92ce0a302acf76c86bddf45f9604836104838
+size 1185529

tqc-Pendulum-v1/data

@@ -0,0 +1,118 @@
+{
+    "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 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 0x7f9908ee34c0>",
+        "_build": "<function TQCPolicy._build at 0x7f9908ee3550>",
+        "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7f9908ee35e0>",
+        "reset_noise": "<function TQCPolicy.reset_noise at 0x7f9908ee3670>",
+        "make_actor": "<function TQCPolicy.make_actor at 0x7f9908ee3700>",
+        "make_critic": "<function TQCPolicy.make_critic at 0x7f9908ee3790>",
+        "forward": "<function TQCPolicy.forward at 0x7f9908ee3820>",
+        "_predict": "<function TQCPolicy._predict at 0x7f9908ee38b0>",
+        "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7f9908ee3940>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f9908ee4080>"
+    },
+    "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": 1670944979782316322,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/Pendulum-v1__tqc__2735755449__1670944977/Pendulum-v1",
+    "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:": "gAWVgQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAAFn4fz8IWHo8ZMJcPZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////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: PyTorch 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        Cannot be used in combination with handle_timeout_termination.\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 0x7f990936a430>",
+        "add": "<function ReplayBuffer.add at 0x7f990936a4c0>",
+        "sample": "<function ReplayBuffer.sample at 0x7f990936a550>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f990936a5e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f99093691c0>"
+    },
+    "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,
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

tqc-Pendulum-v1/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a2234886eeacc4e1394d8368adbe4ebb632499c2a4d78c7e3ade9fb6dd20e7a
+size 1507

tqc-Pendulum-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04908edf2f374e9bc6fdf3ca108fa22749d368439ca7a2e0da75c69f5a5fad6a
+size 1456133

tqc-Pendulum-v1/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e62211ce155c382e773b4f2df5c7bd60e100f2939d830124da0292eb29f606
+size 747

tqc-Pendulum-v1/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
+- Python: 3.9.12
+- Stable-Baselines3: 1.8.0a6
+- PyTorch: 1.13.1+cu117
+- GPU Enabled: True
+- Numpy: 1.24.1
+- Gym: 0.21.0

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f122884d74ce606da3c99086d26de6a3a6d8728eb2ee492ac9c83da13d5bf4b
+size 2884