lerobot-clone

mirror of https://github.com/huggingface/lerobot.git synced 2026-05-31 19:01:28 +00:00

Files

Michel Aractingi 795063aa1b - Fixed big issue in the loading of the policy parameters sent by the learner to the actor -- pass only the actor to the update_policy_parameters and remove strict=False

- Fixed big issue in the normalization of the actions in the `forward` function of the critic -- remove the `torch.no_grad` decorator in `normalize.py` in the normalization function
- Fixed performance issue to boost the optimization frequency by setting the storage device to be the same as the device of learning.

Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com>

2025-03-28 17:18:24 +00:00

actor_server.py

- Fixed big issue in the loading of the policy parameters sent by the learner to the actor -- pass only the actor to the update_policy_parameters and remove strict=False

2025-03-28 17:18:24 +00:00

buffer.py

Fixed bug in the action scale of the intervention actions and offline dataset actions. (scale by inverse delta)

2025-03-28 17:18:24 +00:00

crop_dataset_roi.py

Fixed bug in the action scale of the intervention actions and offline dataset actions. (scale by inverse delta)

2025-03-28 17:18:24 +00:00

find_joint_limits.py

- Added JointMaskingActionSpace wrapper in gym_manipulator in order to select which joints will be controlled. For example, we can disable the gripper actions for some tasks.