ydy0615/lerobot-clone
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-05-31 02:41:24 +00:00
Code Issues Packages Projects Releases Wiki Activity
988 Commits 205 Branches 9 Tags
ad132c9c39c69af2d4c8d95ade2cded80fdedb71
Commit Graph

354 Commits

Author SHA1 Message Date
Adil Zouitine
ad132c9c39 [HIL SERL] Env management and add gym-hil (#1077) 
Co-authored-by: Michel Aractingi <michel.aractingi@gmail.com>
 2025-05-07 09:39:21 +02:00
Adil Zouitine
70d55c77e9 Merge branch 'main' into user/adil-zouitine/2025-1-7-port-hil-serl-new 2025-05-06 16:43:44 +02:00
Michel Aractingi
5998203a33 [Port HIL-SERL] Final fixes for reward classifier (#1067) 
Co-authored-by: s1lent4gnt <kmeftah.khalil@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2025-05-05 11:33:09 +02:00
omahs
8cfab38824 Fix typos (#1070) 2025-05-05 10:35:32 +02:00
AdilZouitine
fb7c288c94 Update torch.load calls in network_utils.py to include weights_only=False, to ensure no regression with torch 2.6 update 2025-04-29 18:23:51 +02:00
AdilZouitine
4257fe5045 rename reward classifier 2025-04-25 18:38:52 +02:00
Michel Aractingi
bd4db8d747 [Port HIl-Serl] Refactor gym-manipulator (#1034) 2025-04-25 16:34:54 +02:00
AdilZouitine
a8da4a347e Clean the code 2025-04-24 17:22:54 +02:00
AdilZouitine
b8c2b0bb93 Clean the code and remove todo 2025-04-24 16:10:56 +02:00
Adil Zouitine
c58b504a9e [HIL-SERL]Remove overstrict pre-commit modifications (#1028) 2025-04-24 13:48:52 +02:00
Adil Zouitine
299effe0f1 [HIL-SERL] Update CI to allow installation of prerelease versions for lerobot (#1018) 
Co-authored-by: imstevenpmwork <steven.palma@huggingface.co>
 2025-04-24 10:18:03 +02:00
AdilZouitine
b77cee7cc6 Ignore spellcheck for ik variable 2025-04-22 13:19:59 +00:00
AdilZouitine
6230840397 Fix linter issue part 2 2025-04-22 10:56:23 +02:00
AdilZouitine
c5845ee203 Fix linter issue 2025-04-22 10:37:08 +02:00
Eugene Mironov
0030ff3f74 [HIL-SERl PORT] Unit tests for Replay Buffer (#966) 2025-04-22 09:35:57 +02:00
Michel Aractingi
dc726cb9a3 Refactor crop_dataset_roi 2025-04-22 09:31:35 +02:00
AdilZouitine
a7a51cfc9c Refactor SACPolicy and configuration to replace 'grasp_critic' terminology with 'discrete_critic'. Update related methods and comments for clarity and consistency in handling discrete actions. 2025-04-18 14:57:03 +00:00
pre-commit-ci[bot]
0d70f0b85c [pre-commit.ci] auto fixes from pre-commit.com hooks 
for more information, see https://pre-commit.ci
 2025-04-18 14:22:11 +00:00
Michel Aractingi
c1ee25d9f7 nits in configuration classifier and control_robot 2025-04-18 16:18:13 +02:00
Michel Aractingi
9886520d33 Added option to add current readings to the state of the policy 2025-04-18 16:18:13 +02:00
Michel Aractingi
3b24ad3c84 Fixes for the reward classifier 2025-04-18 16:18:13 +02:00
pre-commit-ci[bot]
fb92935601 [pre-commit.ci] auto fixes from pre-commit.com hooks 
for more information, see https://pre-commit.ci
 2025-04-18 13:33:37 +00:00
AdilZouitine
2f7339b410 Handle caching 
Co-authored-by: s1lent4gnt <kmeftah.khalil@gmail.com>
 2025-04-18 15:10:22 +02:00
AdilZouitine
8122721f6d match target entropy hil serl 
Co-authored-by: s1lent4gnt <kmeftah.khalil@gmail.com>
 2025-04-18 15:10:22 +02:00
AdilZouitine
9386892f8e Refactor modeling_sac and parameter handling for clarity and reusability. 
Co-authored-by: s1lent4gnt <kmeftah.khalil@gmail.com>
 2025-04-18 15:10:22 +02:00
pre-commit-ci[bot]
28b595c651 [pre-commit.ci] auto fixes from pre-commit.com hooks 
for more information, see https://pre-commit.ci
 2025-04-18 15:10:22 +02:00
Michel Aractingi
9fd4c21d4d General fixes in code, removed delta action, fixed grasp penalty, added logic to put gripper reward in info 2025-04-18 15:10:22 +02:00
AdilZouitine
e18274bc9a fix caching and dataset stats is optional 2025-04-18 15:10:22 +02:00
pre-commit-ci[bot]
a3ada81816 [pre-commit.ci] auto fixes from pre-commit.com hooks 
for more information, see https://pre-commit.ci
 2025-04-18 15:10:22 +02:00
AdilZouitine
78c640b6d8 Refactor complementary_info handling in ReplayBuffer 2025-04-18 15:10:22 +02:00
AdilZouitine
d5a87f67cf Handle gripper penalty 2025-04-18 15:10:22 +02:00
AdilZouitine
8bcf41761d fix caching 2025-04-18 15:10:22 +02:00
pre-commit-ci[bot]
1efaf02df9 [pre-commit.ci] auto fixes from pre-commit.com hooks 
for more information, see https://pre-commit.ci
 2025-04-18 15:10:22 +02:00
AdilZouitine
cf58890bb0 fix indentation issue 2025-04-18 15:10:22 +02:00
AdilZouitine
7c2c67fc3c Enhance SAC configuration and replay buffer with asynchronous prefetching support 
- Added async_prefetch parameter to SACConfig for improved buffer management.
- Implemented get_iterator method in ReplayBuffer to support asynchronous prefetching of batches.
- Updated learner_server to utilize the new iterator for online and offline sampling, enhancing training efficiency.
 2025-04-18 15:10:22 +02:00
AdilZouitine
6167886472 Enhance SACPolicy and learner server for improved grasp critic integration 
- Updated SACPolicy to conditionally compute grasp critic losses based on the presence of discrete actions.
- Refactored the forward method to handle grasp critic model selection and loss computation more clearly.
- Adjusted learner server to utilize optimized parameters for grasp critic during training.
- Improved action handling in the ManiskillMockGripperWrapper to accommodate both tuple and single action inputs.
 2025-04-18 15:10:22 +02:00
AdilZouitine
f9fb9d4594 Refactor SACPolicy for improved readability and action dimension handling 
- Cleaned up code formatting for better readability, including consistent spacing and removal of unnecessary blank lines.
- Consolidated continuous action dimension calculation to enhance clarity and maintainability.
- Simplified loss return statements in the forward method to improve code structure.
- Ensured grasp critic parameters are included conditionally based on configuration settings.
 2025-04-18 15:10:22 +02:00
AdilZouitine
d86d29fe21 Add mock gripper support and enhance SAC policy action handling 
- Introduced mock_gripper parameter in ManiskillEnvConfig to enable gripper simulation.
- Added ManiskillMockGripperWrapper to adjust action space for environments with discrete actions.
- Updated SACPolicy to compute continuous action dimensions correctly, ensuring compatibility with the new gripper setup.
- Refactored action handling in the training loop to accommodate the changes in action dimensions.
 2025-04-18 15:10:22 +02:00
AdilZouitine
f83d215e7a Refactor SAC policy and training loop to enhance discrete action support 
- Updated SACPolicy to conditionally compute losses for grasp critic based on num_discrete_actions.
- Simplified forward method to return loss outputs as a dictionary for better clarity.
- Adjusted learner_server to handle both main and grasp critic losses during training.
- Ensured optimizers are created conditionally for grasp critic based on configuration settings.
 2025-04-18 15:10:22 +02:00
Michel Aractingi
0cce2fe0fa Added Gripper quantization wrapper and grasp penalty 
removed complementary info from buffer and learner server
removed get_gripper_action function
added gripper parameters to `common/envs/configs.py`
 2025-04-18 15:10:22 +02:00
pre-commit-ci[bot]
88d26ae976 [pre-commit.ci] auto fixes from pre-commit.com hooks 
for more information, see https://pre-commit.ci
 2025-04-18 15:10:22 +02:00
s1lent4gnt
3a2308d86f Add grasp critic to the training loop 
- Integrated the grasp critic gradient update to the training loop in learner_server
- Added Adam optimizer and configured grasp critic learning rate in configuration_sac
- Added target critics networks update after the critics gradient step
 2025-04-18 15:10:22 +02:00
s1lent4gnt
fdd04efdb7 Add get_gripper_action method to GamepadController 2025-04-18 15:10:22 +02:00
s1lent4gnt
ff18be18ad Add gripper penalty wrapper 2025-04-18 15:10:22 +02:00
s1lent4gnt
427720426b Add complementary info in the replay buffer 
- Added complementary info in the add method
- Added complementary info in the sample method
 2025-04-18 15:10:22 +02:00
pre-commit-ci[bot]
334cf8143e [pre-commit.ci] auto fixes from pre-commit.com hooks 
for more information, see https://pre-commit.ci
 2025-04-18 15:10:22 +02:00
AdilZouitine
5b49601072 Fix convergence of sac, multiple torch compile on the same model caused divergence 2025-04-18 15:10:22 +02:00
AdilZouitine
0185a0b6fd Fix cuda graph break 2025-04-18 15:10:22 +02:00
s1lent4gnt
70d418935d Fix: Prevent Invalid next_state References When optimize_memory=True (#918) 2025-04-18 15:10:22 +02:00
pre-commit-ci[bot]
eb44a06a9b [pre-commit.ci] auto fixes from pre-commit.com hooks 
for more information, see https://pre-commit.ci
 2025-04-18 15:10:22 +02:00