Robotics: Science and Systems VIII

On Stochastic Optimal Control and Reinforcement Learning by Approximate Inference

Konrad Rawlik, Marc Toussaint, Sethu Vijayakumar

Abstract:

We present a reformulation of the stochastic optimal control problem in terms of $

Download:

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} 
}