- 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.
- 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>
This commit is contained in:
@@ -40,6 +40,7 @@ def find_joint_bounds(
|
||||
min = np.min(np.stack(pos_list), 0)
|
||||
print(f"Max angle position per joint {max}")
|
||||
print(f"Min angle position per joint {min}")
|
||||
break
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
Reference in New Issue
Block a user