wanxinjin / Learning-from-Sparse-Demonstrations

A framework and method to jointly learn a (neural) control objective function and a time-warping function only from sparse demonstrations or waypoints.

https://wanxinjin.github.io/posts/lfsd

robotarm_random.py don't have a dg

glasslucas00 opened this issue 2 years ago · comments

glasslucas00 commented 2 years ago

It should be a g;
so I change env.initDyn(l1=1, m1=1, l2=1, m2=1, dg=0) to env.initDyn(l1=1, m1=1, l2=1, m2=1, g=0) and it works

WANXIN JIN commented 2 years ago

Thank you, @glasslucas00, for reporting this bug. I have just fixed it.
https://github.com/wanxinjin/Learning-from-Sparse-Demonstrations/blob/master/Examples/robotarm_random.py

thank you for your interest in this work.