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 +1,75 @@
+---
+library_name: stable-baselines3
+tags:
+- ReachCube-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TQC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: ReachCube-v0
+      type: ReachCube-v0
+    metrics:
+    - type: mean_reward
+      value: -88.83 +/- 25.22
+      name: mean_reward
+      verified: false
+---
+
+# **TQC** Agent playing **ReachCube-v0**
+This is a trained model of a **TQC** agent playing **ReachCube-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 ReachCube-v0 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo tqc --env ReachCube-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 ReachCube-v0 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo tqc --env ReachCube-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo tqc --env ReachCube-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo tqc --env ReachCube-v0 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('n_envs', 16),
+             ('n_timesteps', 10000000.0),
+             ('policy', 'MultiInputPolicy'),
+             ('use_sde', True),
+             ('normalize', False)])
+```
+
+# Environment Arguments
+```python
+{'observation_mode': 'state', 'render_mode': 'rgb_array'}
+```

args.yml

@@ -0,0 +1,83 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - tqc
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - ReachCube-v0
+  - - env_kwargs
+    - observation_mode: state
+  - - eval_env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - - gym_lowcostrobot
+  - - hyperparams
+    - null
+  - - 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
+    - 1136752841
+  - - 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 +1,9 @@
+!!python/object/apply:collections.OrderedDict
+- - - n_envs
+    - 16
+  - - n_timesteps
+    - 10000000.0
+  - - policy
+    - MultiInputPolicy
+  - - use_sde
+    - true

env_kwargs.yml

@@ -0,0 +1,2 @@
+observation_mode: state
+render_mode: rgb_array

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c24c30e8305c5c256e7b514ecae774ba762e2adee6290ee23e7d812cf8703c
+size 634168

results.json

@@ -0,0 +1 @@
+{"mean_reward": -88.82967179999999, "std_reward": 25.21824856666716, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-13T14:19:17.697076"}

tqc-ReachCube-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c466b6744c30b156789d3c18d571c61a723e6343abdded782d6d246b62c7ead
+size 3417949

tqc-ReachCube-v0/_stable_baselines3_version

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

tqc-ReachCube-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67307836e6df450c7bdac0b9ab034276a1948724858a89d8368afad7e721092c
+size 589975

tqc-ReachCube-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c50f4b4b53783ddcbae9e951faaefadb82f844c6edc6d384c6e9d49c8735107
+size 1255594

tqc-ReachCube-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 0x7fb40930f7f0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fb409313dc0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "use_sde": true
+    },
+    "num_timesteps": 274912,
+    "_total_timesteps": 10000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1718287943030623139,
+    "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": "[[-1.4861529  -0.53421587  0.35194027  0.4307574  -0.26268917 -1.5479153 ]\n [-1.638025   -0.5787811   0.39530036  0.39185637 -0.6268942  -1.3910425 ]\n [-1.456556   -0.24814238  0.01990645  0.3462921  -0.6303778  -1.5521125 ]\n [-1.519424   -0.46675706  0.13337381  0.399494   -0.64106584 -1.350275  ]\n [-1.6711924  -0.62343425  0.3633514   0.29745853 -0.8751136  -1.4887573 ]\n [-1.5406705  -0.4373416   0.03418196  0.08696669 -0.5389243  -1.5566221 ]\n [-1.468259   -0.43134266  0.14222708  0.55254525 -0.44336784 -1.3638334 ]\n [-1.1646994  -0.57488775  0.19283354  0.17738208 -0.3768603  -1.0309021 ]\n [-1.2812357  -0.55190617  0.38103217  0.08408184 -0.666272   -1.1738621 ]\n [-1.7872136  -0.37607324  0.17362891  0.47947946 -0.37330005 -1.4980302 ]\n [-1.75561    -0.27742842  0.06946681  0.513473   -0.716419   -1.3112395 ]\n [-1.1488262  -0.6538635   0.4061106   0.4104307  -0.48219362 -1.5940045 ]\n [-1.4813718  -0.2619098   0.18801475  0.18802969 -0.6807912  -1.4330996 ]\n [-1.4238217  -0.41568005  0.17163447  0.4589017  -0.53347313 -1.3292749 ]\n [-1.577927   -0.26630813  0.24133372  0.59634066 -0.7243273  -1.4628471 ]\n [-1.6353616  -0.5274257   0.28991976  0.39210486 -0.64225835 -1.3234297 ]]",
+        "arm_qvel": "[[-3.2170682   1.3324435  -2.780542    2.9448714  -4.9733357  -4.9594913 ]\n [-1.3275044  -1.7657375   2.8621466  -3.7970567   4.9559636  -5.007292  ]\n [-3.3994691  -0.24946617 -0.31370345 -2.3618612   5.011525    4.47577   ]\n [-3.5980883   0.47867066 -0.31971142 -2.8385425   4.660123   -4.939568  ]\n [-1.5630292   0.0548422  -0.21619356  2.2235198   4.631214   -4.8903623 ]\n [-2.6139853  -1.455348    3.1191103   5.3625283   4.621226   -4.9399443 ]\n [-3.575686    0.06286749  2.3101249   5.550919    5.0007443  -4.9607253 ]\n [ 2.0088804   4.5502524  -1.6358457  -6.1800356   5.020014   -5.0140862 ]\n [-2.9883015  -2.031093   -1.8920774  -5.789776    4.9867682   4.971437  ]\n [-1.9127936   2.357551   -0.90013295  3.2961636   4.173175    5.056108  ]\n [-2.4428768  -1.2813135  -2.5762322  -4.4475074   4.621809    5.022138  ]\n [-1.1635257   1.9401635  -2.973139    3.066862    4.6497173  -4.993203  ]\n [-3.2894876   2.0774593  -3.5364778   4.4471855  -4.999317   -3.8035111 ]\n [-3.614219    0.2942863  -1.7024422   3.9847198  -5.007257   -4.9225454 ]\n [-1.5529131   3.7619503   0.48336926 -2.3998318  -4.964937   -4.954885  ]\n [-1.4702449   0.17748345 -2.6446817  -1.8314     -4.6458263   5.070767  ]]",
+        "cube_pos": "[[-0.07315578  0.22903675  0.01498293]\n [-0.08827455  0.11891069  0.01498293]\n [ 0.10610168  0.13741066  0.01498293]\n [-0.00207315  0.13141002  0.01498293]\n [-0.05411569  0.12038758  0.01498293]\n [ 0.11790938  0.11430328  0.01498293]\n [-0.10604545  0.18555033  0.01498293]\n [-0.0481476   0.21147203  0.01498293]\n [-0.13804555  0.1549193   0.01498293]\n [ 0.07147329  0.20422019  0.01498293]\n [ 0.07803696  0.14240408  0.01498293]\n [-0.10916655  0.15740444  0.01498293]\n [-0.08762953  0.22623463  0.01498293]\n [ 0.00096487  0.22933191  0.01498293]\n [ 0.03391898  0.1718271   0.01498293]\n [-0.04066069  0.18667582  0.01498293]]"
+    },
+    "_episode_num": 544,
+    "use_sde": true,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.9725104,
+    "_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": 17175,
+    "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 0x7fb409cc23b0>",
+        "add": "<function DictReplayBuffer.add at 0x7fb409cc2440>",
+        "sample": "<function DictReplayBuffer.sample at 0x7fb409cc24d0>",
+        "_get_samples": "<function DictReplayBuffer._get_samples at 0x7fb409cc2560>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fb409cbc7c0>"
+    },
+    "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-ReachCube-v0/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17b7ed5d998129b0796ae12e6def14aeb19772f9668df0d97db962faa2a6933b
+size 1940

tqc-ReachCube-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0911d58b701bd6ae234a5829d5d010bb5602eed2875cf42b01c6dc1d7deb3bc
+size 1548985

tqc-ReachCube-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5384239c46a43e144ebbd9ef0e393566e8bf12e44fcc65c33c09f51535b3485
+size 1180

tqc-ReachCube-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 sha256:9840e2b54bd09c949aaab0e7820b9a9dc8252b66c499fdb51fc72189759b61f3
+size 25881