Michel Aractingi ff47c0b0d3 - 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>		2025-02-19 16:22:51 +00:00
..
datasets	Modified crop_dataset_roi interface to automatically write the cropped parameters to a json file in the meta of the dataset	2025-02-14 12:32:45 +01:00
envs	- Added `lerobot/scripts/server/gym_manipulator.py` that contains all the necessary wrappers to run a gym-style env around the real robot.	2025-02-06 16:29:37 +01:00
policies	- 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`	2025-02-19 16:22:51 +00:00
robot_devices	Added possiblity to record and replay delta actions during teleoperation rather than absolute actions	2025-02-12 19:25:41 +01:00
utils	Several fixes to move the actor_server and learner_server code from the maniskill environment to the real robot environment.	2025-02-10 16:03:39 +01:00
logger.py	Improve wandb logging and custom step tracking in logger	2025-02-17 10:08:49 +00:00