Add explicit contact params to peg geom to fix peg-insert-side under mujoco>=3.4 - #578
Add explicit contact params to peg geom to fix peg-insert-side under mujoco>=3.4#578rainx0r wants to merge 3 commits into
Conversation
…mujoco>=3.4 MuJoCo 3.4 fixed a box-box collision behaviour bug, which in turn broke peg-insert-side. Copying over the contact params from the gripper pads in xyz_base.xml and making them explicit on the peg rather than using the defaults seems to fix it.
|
@rainx0r CI passes, I will run some single task experiments over the weekend to see how things are affected. |
|
I did actually run some single task experiments already and it seems like learning behaviour isn't identical, but it's somewhat similar. I have some WIP work trying to use optimisation to find the correct contact parameters such that after using a newer MuJoCo version the environment behaviour is more similar to the current version / contact params (what my second commit does) but it's not yet complete. I need to double check how close the trajectories are and report back, I believe it matches closely but the learning dynamics are still not the same as the old version so I was going to investigate further. I also ran some MT10 experiments and it seems like the difference in downstream learning that setting is less pronounced than in MT1 experiments. |
|
@rainx0r can you show some logs/performance curves that higlight these differences? |
MuJoCo 3.4 fixed a box-box collision behaviour bug, which in turn broke peg-insert-side. Copying over the contact params from the gripper pads in xyz_base.xml and making them explicit on the peg rather than using the defaults seems to fix it.
This does change the environment dynamics, but also so does the MuJoCo 3.4 box-box collision bug fix.
Draft status
What remains to be done is:
peg-insert-side-v3before/after the collision parameter change, on MuJoCo 3.3, to see how it affects policy learningpeg-insert-side-v3on MuJoCo 3.8.1 using this patch and compare qualitatively and quantitatively the policy and learning dynamics to the unchanged MuJoCo 3.3 environment