admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-05-22 03:59:42 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,435 Commits 203 Branches 9 Tags
feat/leader-arm-intervention-pr2596
Commit Graph

1435 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Khalil Meftah 05764da0f1 disable rotation 2026-04-28 15:04:05 +02:00
Khalil Meftah f40a36fe82 diable rotation 2026-04-28 13:29:31 +02:00
Khalil Meftah 9b538d6cbf fix follower shakiness and space-bar trigger 2026-04-28 13:11:59 +02:00
Khalil Meftah a59900a339 fix missing kwargs 2026-04-28 12:17:24 +02:00
Khalil Meftah 5cea61708d add so100 leader as hil teleoperation 2026-04-28 11:46:21 +02:00
Khalil Meftah ef6b3b5b0f refactor: simplify docstrings for clarity and conciseness across multiple files 2026-04-28 11:11:02 +02:00
Khalil Meftah e298474bf3 fix(tests): gate RL tests on the datasets extra 2026-04-27 16:53:34 +02:00
Khalil Meftah 577f14337a refactor(tests): remove grpc import checks from test files for cleaner code 2026-04-27 16:20:13 +02:00
Khalil Meftah 47be90f040 refactor(rl): make RLAlgorithmConfig an abstract base class for better extensibility 2026-04-27 15:59:59 +02:00
Khalil Meftah 47dd65347e refactor(rl): add type property to RLAlgorithmConfig for better clarity 2026-04-27 15:57:24 +02:00
Khalil Meftah fd5a788120 refactor(rl): add make_algorithm_config function for RLAlgorithmConfig instantiation 2026-04-27 15:55:16 +02:00
Khalil Meftah 9ce9e01469 refactor(rl): make algorithm a nested config so all SAC hyperparameters are JSON-addressable 2026-04-27 13:39:03 +02:00
Khalil Meftah 21c16a27f0 Revert "perf(observation_processor): add CUDA support for image processing" 
This reverts commit 38b88c414c.
 2026-04-27 11:52:19 +02:00
Khalil Meftah b3164543f4 fix(rl): enhance intervention handling in actor and learner 
(cherry picked from commit ef8bfffbd7)
 2026-04-27 11:35:21 +02:00
Khalil Meftah f3993cbbb1 fix(rl): improve action processing for discrete and continuous actions 
(cherry picked from commit f887ab3f6a)
 2026-04-27 11:35:20 +02:00
Khalil Meftah c278cfa026 fix(rl): postprocess action in actor 
(cherry picked from commit c2556439e5)
 2026-04-27 11:35:20 +02:00
Khalil Meftah 77d18659b1 fix(rl): mirror gym_manipulator in actor 
(cherry picked from commit d2a046dfc5)
 2026-04-27 11:35:19 +02:00
Khalil Meftah 6347edefb1 fix(rl): merge environment and action-processor info in transition processing 
(cherry picked from commit 30e1886b64)
 2026-04-27 11:35:18 +02:00
Khalil Meftah eda47eca18 fix(rl): update neutral gripper action 
(cherry picked from commit 9c9064e5be)
 2026-04-27 11:35:18 +02:00
Khalil Meftah a64e6f5070 fix(rl): clarify discrete gripper action mapping in GripperVelocityToJoint for SO100 
(cherry picked from commit 494f469a2b)
 2026-04-27 11:35:17 +02:00
Khalil Meftah 3def86c2c3 fix(rl): add time limit processor to environment pipeline 
(cherry picked from commit cd105f65cb)
 2026-04-27 11:35:17 +02:00
Khalil Meftah 356a64d8c4 fix(rl): correctly wire HIL-SERL gripper penalty through processor pipeline 
(cherry picked from commit 9c2af818ff)
 2026-04-27 11:35:16 +02:00
Khalil Meftah 38b88c414c perf(observation_processor): add CUDA support for image processing 2026-04-24 13:36:26 +02:00
Khalil Meftah 1ed32210c7 refactor(rl/sac): consolidate hyperparameter ownership and clean up discrete critic 2026-04-24 13:18:33 +02:00
Khalil Meftah 06255996ea refactor(policies): rename policies/sac → policies/gaussian_actor 2026-04-23 19:13:18 +02:00
Khalil Meftah 8065bf15c7 fix test for flat dict structure 2026-04-21 12:06:25 +02:00
Khalil Meftah 8191d2d87f remove unused type alias 2026-04-21 11:56:27 +02:00
Khalil Meftah 6b93f31238 fix docstring 2026-04-21 11:55:17 +02:00
Khalil Meftah a4c0c9e358 update losses names in tests 2026-04-21 11:53:32 +02:00
Khalil Meftah a84b0e8132 refactor(sac): decouple algorithm hyperparameters from policy config 2026-04-18 16:40:56 +02:00
Khalil Meftah 2487a6ee6d perf(rl): use async iterators in OnlineOfflineMixer.get_iterator 2026-04-18 16:02:28 +02:00
Khalil Meftah 72fb0faf62 refactor(sac): simplify optimizer return structure 2026-04-18 15:45:22 +02:00
Khalil Meftah 2c97cb23c8 refactor(rl): update shutdown_event type hints from 'any' to 'Any' for consistency and clarity 2026-04-18 15:39:32 +02:00
Khalil Meftah 87d4c9879c fix(sac): clarify torch.compile status 2026-04-18 15:19:35 +02:00
Khalil Meftah e4c1a8472d fix(config): update vision encoder model name to lerobot/resnet10 2026-04-18 15:15:59 +02:00
Khalil Meftah d7e25c8326 refactor(rl): expose public API in rl/__init__ and use relative imports in sub-packages 2026-04-16 15:46:34 +02:00
Khalil Meftah a5ad273b62 fix(tests): skip tests that require grpc if not available 2026-04-15 16:30:20 +02:00
Khalil Meftah 23bece96a4 fix(tests): ensure tensor stats comparison accounts for reshaping in normalization tests 2026-04-15 16:12:08 +02:00
Khalil Meftah 7a1c9e74c3 fix: skip tests that require grpc if not available 2026-04-15 15:18:04 +02:00
Khalil Meftah c88cf979f1 fix: use string key for IS_INTERVENTION in complementary_info to avoid torch.load serialization error 2026-04-15 11:49:38 +02:00
Khalil Meftah 79a9ebdaa6 fix: add try/finally to control_loop to ensure image writer cleanup on exit 2026-04-14 17:54:35 +02:00
Khalil Meftah da6e36fd03 Merge remote-tracking branch 'origin/main' into user/khalil-meftah/2026-02-16-rl-stack-refactor 2026-04-14 17:14:56 +02:00
Khalil Meftah 64dc08cb7b fix: include IS_INTERVENTION in complementary_info sent to learner for offline replay buffer 2026-04-14 16:35:08 +02:00
Radu 1ede000bdd fix(rl): swap dict merge order to preserve teleop intervention flag (#3273) 
Co-authored-by: Khalil Meftah <khalil.meftah@huggingface.co>
 2026-04-14 16:20:54 +02:00
Khalil Meftah d57c58a532 fix: add thread synchronization to ReplayBuffer to prevent race condition between add() and sample() (#3372) 2026-04-14 13:16:45 +02:00
Matteo Tiezzi b3e76a92f2 fix(groot): compatibility fixes for gr00t in v0.5 (#3182) 
* fix(groot): apply groot 0.5 fixes

* fix(groot): correct indentation and add tile count in Eagle25VL processor

* Fixed lint7/style
 2026-04-14 13:09:18 +02:00
Khalil Meftah f5c801fd34 fix(test): add missing device placement in multi-task DiT tests (#3349) 2026-04-14 12:25:29 +02:00
Ethan Pronovost cff4bcf4a0 Update reward classifier training config (#3147) 
Co-authored-by: Khalil Meftah <khalil.meftah@huggingface.co>
 2026-04-14 11:28:49 +02:00
Khalil Meftah e6d282108d Fix: add kwargs in reward classifier __init__() 2026-04-14 11:13:43 +02:00
Maxime Ellerbach a656a982af fix(feetech): motor position readings overflow (#3373) 2026-04-13 22:39:58 +02:00