-
Notifications
You must be signed in to change notification settings - Fork 117
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Basic arm reaching environment created, myoArmReachRandom-v0 #232
base: dev
Are you sure you want to change the base?
Conversation
Looks good to me. Next step will be train a policy to ensure all parameters are playing well. |
BUGFIX: Fix object-target proximity threshold
2.8.3 release
BUGFIX: Manipulation ENV
Use model that has no hand or hand muscles
Add fixed and random arm reach environments.
Re-run checks
Following Vittorio's advice, I have created a myoArm model that has no hand or hand muscles (see myo_sim PR 29). I have created a fixed and random variant of the task:
Results of training for the fixed and random variants of the environment look good to me. |
Vittorio suggested to include the hand bones and joints for the reaching tasks (previously excluded) and just exclude the hand tendons and muscles. The file has been updated to reflect this change.
Vittorio suggested to include the hand bones and joints (previously excluded) and only exclude the hand tendons and muscles. I've done this and trained a SAC policy on the random variant of the task. Here are the training results. |
@jamesheald could you take a look at the failing test? You can run them locally with: It would be quite useful to get this in. |
Hey @P-Schumacher. I think this is failing because it depends on a yet-to-be-accepted PR in the simhive repo. I have the required xml files in my local simhive directory and it works for me. |
I have created a basic environment for reaching to random targets in space with the MyoSuite arm.