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 +1,70 @@
+---
+library_name: stable-baselines3
+tags:
+- Hopper-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TQC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Hopper-v3
+      type: Hopper-v3
+    metrics:
+    - type: mean_reward
+      value: 3318.43 +/- 590.11
+      name: mean_reward
+      verified: false
+---
+
+# **TQC** Agent playing **Hopper-v3**
+This is a trained model of a **TQC** agent playing **Hopper-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
+
+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 Hopper-v3 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo tqc --env Hopper-v3  -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 Hopper-v3 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo tqc --env Hopper-v3  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo tqc --env Hopper-v3 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo tqc --env Hopper-v3 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('learning_starts', 10000),
+             ('n_timesteps', 1000000.0),
+             ('policy', 'MlpPolicy'),
+             ('top_quantiles_to_drop_per_net', 5),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,83 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - tqc
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - Hopper-v3
+  - - 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
+    - 1489988575
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/Hopper-v3__tqc__1489988575__1675911799
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - openrlbenchmark
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,9 @@
+!!python/object/apply:collections.OrderedDict
+- - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 1000000.0
+  - - policy
+    - MlpPolicy
+  - - top_quantiles_to_drop_per_net
+    - 5

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd9170f8581f7f67ccb76a43201d0aaf67f9571e736957d4691e4677ed056ce9
+size 1506620

results.json

@@ -0,0 +1 @@
+{"mean_reward": 3318.432228, "std_reward": 590.1117810663247, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T15:50:17.126240"}

tqc-Hopper-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b702270f57059af3d761f6de6442e1196a7284b05f0e140094b4994f9c0cd72a
+size 3328083

tqc-Hopper-v3/_stable_baselines3_version

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

tqc-Hopper-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5522f81cdac034526738cabb6514b19cba024def77ecf6d0f09ae338614d2386
+size 569757

tqc-Hopper-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9b2cfb849d2557fc4840a49a1c606ebdc02480fe6c62f10f1a3f8d018a10b71
+size 1226489

tqc-Hopper-v3/data

@@ -0,0 +1,115 @@
+{
+    "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 0x7f42f8b26670>",
+        "_build": "<function TQCPolicy._build at 0x7f42f8b26700>",
+        "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7f42f8b26790>",
+        "reset_noise": "<function TQCPolicy.reset_noise at 0x7f42f8b26820>",
+        "make_actor": "<function TQCPolicy.make_actor at 0x7f42f8b268b0>",
+        "make_critic": "<function TQCPolicy.make_critic at 0x7f42f8b26940>",
+        "forward": "<function TQCPolicy.forward at 0x7f42f8b269d0>",
+        "_predict": "<function TQCPolicy._predict at 0x7f42f8b26a60>",
+        "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7f42f8b26af0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f42f8b28340>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "use_sde": false
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "_shape": [
+            11
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            3
+        ],
+        "low": "[-1. -1. -1.]",
+        "high": "[1. 1. 1.]",
+        "bounded_below": "[ True  True  True]",
+        "bounded_above": "[ True  True  True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1675911807908816431,
+    "learning_rate": 0.0003,
+    "tensorboard_log": "runs/Hopper-v3__tqc__1489988575__1675911799/Hopper-v3",
+    "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:": "gAWVzQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZYAAAAAAAAAEf1gSB3cvM/+ZuLMyTpq7+GWy8+oa/Bvx6hoFtJ02I/egmZKjKNyT81ImSkNB3iP/j+bdL56MO/7FSssxgX8L/uqur3/778v65OS0Y+HnY/hpfwJD2gvj+UjAVudW1weZSMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLC4aUjAFDlHSUUpQu"
+    },
+    "_episode_num": 2430,
+    "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": 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:": "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 0x7f42f8fae5e0>",
+        "add": "<function ReplayBuffer.add at 0x7f42f8fae670>",
+        "sample": "<function ReplayBuffer.sample at 0x7f42f8fae700>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f42f8fae790>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f42f8fa6980>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -3.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "top_quantiles_to_drop_per_net": 5,
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

tqc-Hopper-v3/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8f1aea5a627632d9263d0bdf710b416e62ac9f3fe4449b0c97c6bc9bde35e07
+size 1507

tqc-Hopper-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:884be77c09831c57133ab2c3c2285c0654dbe7d7e8353f5f31cf3bcd89733882
+size 1509381

tqc-Hopper-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:682db91086d13cc4cee642a17c5b252c0b90c0f51490220847cacc41c917dc7a
+size 747

tqc-Hopper-v3/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 sha256:4e8cde208445e3fb20d66b4d1050fde579ab56ea09be3bee1db6d7e0211d226a
+size 81171