This code is a reimplementation of the guided policy search algorithm and LQG-based trajectory optimization, meant to help others understand, reuse, and build upon existing work.
This particular fork of the main repository contains the implementation of mirror descent guided policy search applied to the SUPERball tensegrity robot. More details can be found on the project website. Files of interest include the following:
For full documentation, see rll.berkeley.edu/gps.
The code base is a work in progress. See the FAQ for information on planned future additions to the code.