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: 161.03 +/- 1.07
+      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
+    - 2185068769
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/Hopper-v3__tqc__2185068769__1675945406
+  - - 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:cd223ab82168dfb0fad66baa34d47d82be1cb05ae3bb75c60aeab34ba31d7c54
+size 981267

results.json

@@ -0,0 +1 @@
+{"mean_reward": 161.03294480000002, "std_reward": 1.0698511960110926, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T16:00:40.419937"}

tqc-Hopper-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3173e1ed208dd0543826d0489767c1e5c52c14f05030087d53467a03d709267
+size 3328123

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 sha256:70f34bed749c2e41d43f1efbac7ec02dc7e6cf0f400213bb6e6bccb979d8778d
+size 569757

tqc-Hopper-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ffec9c1d3c1ba6697b87cb289b69623a40bc669574fe42fde36fd89921da42b
+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 0x7f81201e6670>",
+        "_build": "<function TQCPolicy._build at 0x7f81201e6700>",
+        "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7f81201e6790>",
+        "reset_noise": "<function TQCPolicy.reset_noise at 0x7f81201e6820>",
+        "make_actor": "<function TQCPolicy.make_actor at 0x7f81201e68b0>",
+        "make_critic": "<function TQCPolicy.make_critic at 0x7f81201e6940>",
+        "forward": "<function TQCPolicy.forward at 0x7f81201e69d0>",
+        "_predict": "<function TQCPolicy._predict at 0x7f81201e6a60>",
+        "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7f81201e6af0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f81201e4d00>"
+    },
+    "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": 1675945411279550992,
+    "learning_rate": 0.0003,
+    "tensorboard_log": "runs/Hopper-v3__tqc__2185068769__1675945406/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:": "gAWVzQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZYAAAAAAAAAO7YNpY1Tfc/nsqym6zLrz9OiMvz9ia7v/IwO+aQruK/bd4P8Q8T678IH/LDz+EDQOt0g9mC9Pw/OsJCveMA7j8C7E/eEOgGQMZZ9qCcAgPAv42/0YwA/D+UjAVudW1weZSMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLC4aUjAFDlHSUUpQu"
+    },
+    "_episode_num": 2045,
+    "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 0x7f812066e5e0>",
+        "add": "<function ReplayBuffer.add at 0x7f812066e670>",
+        "sample": "<function ReplayBuffer.sample at 0x7f812066e700>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f812066e790>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f8120b15800>"
+    },
+    "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 sha256:38b1862213cc927861b0d534bc54a36c3632758dd4c96cc2ddf16e9a1eaba354
+size 1507

tqc-Hopper-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:360de47a408f58e5263c16f0f487711eddf5af69bf2ee57be7e14d9dc7240e4c
+size 1509381

tqc-Hopper-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02591ecc291195a9f258945d48eb86aae51c181d983e90f4ead0557e3dbb14f5
+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 sha256:09592d0243653f1914f6fcbe7c09a86cfd250440463ef67058d23f56a9a3ce48
+size 70767