- 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:
Michel Aractingi
2025-02-11 11:34:46 +01:00
parent b5f89439ff
commit a7db3959f5
9 changed files with 161 additions and 31 deletions

View File

@@ -15,8 +15,13 @@ calibration_dir: .cache/calibration/so100
# the number of motors in your follower arms.
max_relative_target: null
joint_position_relative_bounds:
min: [-88.50586, 23.81836, 0.87890625, -32.16797, 78.66211, 0.53691274]
max: [84.55078, 187.11914, 145.98633, 101.60156, 146.60156, 88.18792]
min: [-87.09961, 62.402344, 67.23633, 36.035156, 77.34375,
0.53691274]
max: [58.183594, 131.83594, 145.98633, 82.08984, 78.22266,
0.60402685]
# min: [-88.50586, 23.81836, 0.87890625, -32.16797, 78.66211, 0.53691274]
# max: [84.55078, 187.11914, 145.98633, 101.60156, 146.60156, 88.18792]
leader_arms:
main: