Initial commit

.gitattributes

@@ -33,3 +33,4 @@ 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 +1,74 @@
+---
+library_name: stable-baselines3
+tags:
+- LiftCube-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TQC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LiftCube-v0
+      type: LiftCube-v0
+    metrics:
+    - type: mean_reward
+      value: 5.52 +/- 1.92
+      name: mean_reward
+      verified: false
+---
+
+# **TQC** Agent playing **LiftCube-v0**
+This is a trained model of a **TQC** agent playing **LiftCube-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
+
+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 LiftCube-v0 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo tqc --env LiftCube-v0  -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 LiftCube-v0 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo tqc --env LiftCube-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo tqc --env LiftCube-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo tqc --env LiftCube-v0 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('n_envs', 16),
+             ('n_timesteps', 1000000.0),
+             ('policy', 'MultiInputPolicy'),
+             ('normalize', False)])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -0,0 +1,83 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - tqc
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - LiftCube-v0
+  - - env_kwargs
+    - null
+  - - eval_env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - - gym_lowcostrobot
+  - - hyperparams
+    - n_envs: 16
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - 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
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 68914943
+  - - 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
+  - - wandb_tags
+    - []

config.yml

@@ -0,0 +1,7 @@
+!!python/object/apply:collections.OrderedDict
+- - - n_envs
+    - 16
+  - - n_timesteps
+    - 1000000.0
+  - - policy
+    - MultiInputPolicy

env_kwargs.yml

@@ -0,0 +1 @@
+render_mode: rgb_array

results.json

@@ -0,0 +1 @@
+{"mean_reward": 5.5155896, "std_reward": 1.9174329601274307, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-08T16:49:10.551511"}

tqc-LiftCube-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2343f28213b02b2926d7d3885b1e887132102fdb629f3648242037aca8ef6cce
+size 3419898

tqc-LiftCube-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+2.3.2

tqc-LiftCube-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17fee445e9820a2c44d52e51708a3186de91e607dca3ee98178d38e935d46844
+size 590670

tqc-LiftCube-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c361a302af3f9cb7a2f536e9b4327ea3e9015f68a22e2cf1a00a03d6ee819c56
+size 1255594

tqc-LiftCube-v0/data

@@ -0,0 +1,109 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVMQAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu",
+        "__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 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 MultiInputPolicy.__init__ at 0x7fa20e847370>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fa20e856a00>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "use_sde": false
+    },
+    "num_timesteps": 175984,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1717861656528326763,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAEBAQEBAQEBAQEBAQEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'collections.OrderedDict'>",
+        ":serialized:": "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",
+        "arm_qpos": "[[ 3.63909453e-02  1.52514532e-01  2.42326558e-02  1.00000000e+00\n   2.31962061e-18  0.00000000e+00]\n [ 9.52652320e-02  1.43222362e-01  1.19775198e-02  1.00000000e+00\n   8.69907744e-05 -9.55217474e-05]\n [ 1.33297622e-01  1.65875599e-01  2.07948126e-02  1.00000000e+00\n   2.00564932e-18  0.00000000e+00]\n [ 2.83787549e-02  1.36520505e-01  2.10882109e-02  1.00000000e+00\n   2.44902826e-18  0.00000000e+00]\n [-9.69018713e-02  2.48821720e-01  1.45736607e-02  1.00000000e+00\n   1.97474168e-17  0.00000000e+00]\n [-1.64944828e-02  2.15080246e-01  1.74245946e-02  9.83678579e-01\n   2.19684131e-02 -1.78560972e-01]\n [-3.05465478e-02  1.65170163e-01  1.15837026e-02  1.00000000e+00\n   1.61402078e-17  4.40448695e-18]\n [-7.67481178e-02  1.61230579e-01  1.47863366e-02  1.00000000e+00\n   1.87571207e-18  0.00000000e+00]\n [-3.25839669e-02  1.08664230e-01  2.40826849e-02  1.00000000e+00\n   7.25238202e-19  0.00000000e+00]\n [-1.32039905e-01  1.09974675e-01  1.88003387e-02  1.00000000e+00\n   4.94263784e-18  0.00000000e+00]\n [ 6.07194379e-02  1.05540536e-01  1.82890706e-02  1.00000000e+00\n   9.94866253e-18  0.00000000e+00]\n [-8.13936889e-02  1.05446897e-01  2.29457077e-02  1.00000000e+00\n   2.94767073e-18  0.00000000e+00]\n [ 4.62712385e-02  1.17765859e-01  1.24220746e-02  1.00000000e+00\n   1.84997762e-09 -3.33261170e-08]\n [-9.60015059e-02  1.79942086e-01  1.79528855e-02  1.00000000e+00\n   5.57680371e-18  0.00000000e+00]\n [ 1.38941705e-02  2.40972355e-01  1.41335661e-02  1.00000000e+00\n   1.36453633e-17  0.00000000e+00]\n [-4.82377447e-02  1.72417149e-01  2.41697095e-02  1.00000000e+00\n   2.09604297e-19  0.00000000e+00]]",
+        "arm_qvel": "[[-1.02871870e-17  3.21292418e-18 -1.47510558e-01 -2.17439525e-16\n  -6.60725139e-16 -3.37655523e-16]\n [-1.06816558e-04 -1.11293746e-04 -2.24728942e-01  7.59817718e-04\n  -8.31903599e-04  2.37641623e-04]\n [-1.02124322e-17 -7.72169793e-19 -3.59230489e-01  2.13445301e-16\n  -1.80297408e-16 -6.34698331e-17]\n [-3.30172512e-18 -5.90047949e-18 -4.30418998e-01  4.57068613e-16\n  -6.77515383e-17 -1.62504171e-16]\n [-9.24992135e-19 -9.97261871e-19  1.49120288e-02  9.02955320e-17\n  -8.30453932e-17 -2.72515712e-17]\n [-4.62023467e-01 -2.42384493e-01 -2.19370022e-01 -2.22406432e-01\n  -1.35995140e+01  6.78867340e-01]\n [ 8.65129260e-18 -6.40124470e-18 -3.32265496e-02  3.29616280e-16\n   6.58735141e-16  2.93033457e-16]\n [-5.95535506e-19  6.41885538e-19 -5.62357426e-01 -1.88509482e-17\n   1.60775681e-16 -5.35970950e-17]\n [-3.61464486e-18  2.98293943e-19 -1.72505781e-01  1.68039174e-16\n  -1.31312156e-16 -1.13846879e-16]\n [ 8.68880338e-19 -1.06339951e-18 -3.48946482e-01  1.70169043e-18\n   2.48742528e-16 -2.50530323e-16]\n [-4.88237566e-18  8.05909084e-18 -3.53184730e-01 -4.09731568e-16\n   3.16038104e-16 -1.94219176e-16]\n [-1.42932415e-18 -4.81018192e-20 -1.96731225e-01  4.58277382e-17\n  -5.51194490e-18 -2.21996020e-16]\n [ 7.67497177e-09  4.26048030e-10 -1.15140237e-01 -3.01414680e-08\n   5.42978455e-07  2.64270547e-16]\n [ 2.70379162e-18 -3.84736230e-19 -4.18423384e-01  8.94515497e-17\n   4.98797162e-16  1.51887500e-17]\n [-5.31328010e-18  1.71442863e-19 -4.58050847e-01 -6.75693958e-16\n  -9.17182495e-17  2.26994275e-17]\n [-3.76793508e-18  4.40154281e-19 -4.15145159e-01  1.06988354e-16\n  -1.37961404e-16 -1.15991832e-16]]",
+        "cube_pos": "[[ 0.0000000e+00  3.8158808e-02  6.0437746e-02]\n [ 6.7896217e-06  6.7945104e-03  2.1006393e-01]\n [ 0.0000000e+00  1.2600064e-01  2.6327252e-01]\n [ 0.0000000e+00  2.9552126e-02  1.4898105e-01]\n [ 0.0000000e+00 -1.9193260e-02  9.3920782e-02]\n [ 3.1333293e-03  1.3580335e+00 -9.6207094e-01]\n [-1.0557936e-18 -5.0787706e-02  4.7663218e-01]\n [ 0.0000000e+00 -5.4117631e-02  1.7298530e-01]\n [ 0.0000000e+00 -2.3375504e-02  1.3817610e-01]\n [ 0.0000000e+00  1.1284253e-02  1.6534725e-01]\n [ 0.0000000e+00 -3.3894338e-02 -1.3158993e-03]\n [ 0.0000000e+00 -7.7917159e-02  6.1252132e-02]\n [ 3.3438156e-18  1.2797104e-02  3.5050616e-01]\n [ 0.0000000e+00  7.7757039e-03  1.7525481e-01]\n [ 0.0000000e+00  4.7738615e-02  4.7506148e-01]\n [ 0.0000000e+00  7.1842484e-03  4.4869740e-02]]"
+    },
+    "_episode_num": 2369,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.824016,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 10992,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.dict.Dict'>",
+        ":serialized:": "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",
+        "spaces": "OrderedDict([('arm_qpos', Box(-3.1415927, 3.1415927, (6,), float32)), ('arm_qvel', Box(-10.0, 10.0, (6,), float32)), ('cube_pos', Box(-10.0, 10.0, (3,), float32))])",
+        "_shape": null,
+        "dtype": null,
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True]",
+        "_shape": [
+            6
+        ],
+        "low": "[-1. -1. -1. -1. -1. -1.]",
+        "high": "[1. 1. 1. 1. 1. 1.]",
+        "low_repr": "-1.0",
+        "high_repr": "1.0",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "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:": "gAWVOQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwQRGljdFJlcGxheUJ1ZmZlcpSTlC4=",
+        "__module__": "stable_baselines3.common.buffers",
+        "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray], 'next_observations': typing.Dict[str, numpy.ndarray]}",
+        "__doc__": "\n    Dict Replay buffer used in off-policy algorithms like SAC/TD3.\n    Extends the ReplayBuffer to use dictionary observations\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        Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\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 DictReplayBuffer.__init__ at 0x7fa20f205f30>",
+        "add": "<function DictReplayBuffer.add at 0x7fa20f205fc0>",
+        "sample": "<function DictReplayBuffer.sample at 0x7fa20f206050>",
+        "_get_samples": "<function DictReplayBuffer._get_samples at 0x7fa20f2060e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fa20f1f7e00>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -6.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "top_quantiles_to_drop_per_net": 2,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

tqc-LiftCube-v0/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55eb60b347dbb13b9ae1560c1bee65e4784d4091ea428a2023c3f0a12687b48e
+size 1940

tqc-LiftCube-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b48bf20005b406acb6b12089176be1c6527db76a236e3ed9b49d29c9d967097d
+size 1549366

tqc-LiftCube-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1d1bf671d3eb275b486300d9bf6999e42aed557e0de4289d0cb6aee7d3e28ee
+size 1180

tqc-LiftCube-v0/system_info.txt

@@ -0,0 +1,8 @@
+- OS: Linux-5.15.0-1048-aws-x86_64-with-glibc2.31 # 53~20.04.1-Ubuntu SMP Wed Oct 4 16:44:20 UTC 2023
+- Python: 3.10.14
+- Stable-Baselines3: 2.3.2
+- PyTorch: 2.3.1+cu121
+- GPU Enabled: True
+- Numpy: 1.26.4
+- Cloudpickle: 3.0.0
+- Gymnasium: 0.29.1

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a947ec302a315f4de25a02fc357391d9d70e754780f39c3b1b9d1440e848b124
+size 60710