Robotics: Science and Systems VIII
On Stochastic Optimal Control and Reinforcement Learning by Approximate Inference
Konrad Rawlik, Marc Toussaint, Sethu VijayakumarAbstract:
We present a reformulation of the stochastic optimal control problem in terms of $
Bibtex:
@INPROCEEDINGS{Rawlik-RSS-12, AUTHOR = {Konrad Rawlik AND Marc Toussaint AND Sethu Vijayakumar}, TITLE = {On Stochastic Optimal Control and Reinforcement Learning by Approximate Inference}, BOOKTITLE = {Proceedings of Robotics: Science and Systems}, YEAR = {2012}, ADDRESS = {Sydney, Australia}, MONTH = {July}, DOI = {10.15607/RSS.2012.VIII.045} }