- Added Nan detection mechanisms in the actor, learner and gym_manipulator for the case where we encounter nans in the loop. - changed the non-blocking in the `.to(device)` functions to only work for the case of cuda because they were causing nans when running the policy on mps - Added some joint clipping and limits in the env, robot and policy configs. TODO clean this part and make the limits in one config file only. Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com> |
||
---|---|---|
.. | ||
wrappers | ||
actor_server.py | ||
buffer.py | ||
crop_dataset_roi.py | ||
find_joint_limits.py | ||
gym_manipulator.py | ||
hilserl.proto | ||
learner_server.py |