@COMMENT This file was generated by bib2html.pl version 0.94
@COMMENT written by Patrick Riley
@COMMENT This file came from Freek Stulp's publication pages at
@COMMENT http://www-clmc.usc.edu/~stulp/publications
@Article{stulp13robot,
title = {Robot Skill Learning: From Reinforcement Learning to Evolution Strategies},
author = {Freek Stulp and Olivier Sigaud},
journal = {Paladyn. Journal of Behavioral Robotics},
year = {2013},
month = {September},
number = {1},
pages = {49--61},
volume = {4},
abstract = {Due to trends towards searching in parameter space and using reward-weighted averaging, reinforcement learning (RL) algorithms for policy improvement are now able to learn sophisticated robot skills. A side-effect of these trends has been that RL algorithms have become more and more similar to evolution strategies, which treat policy improvement as a black-box optimization problem, and thus do not leverage the problem structure as RL algorithms do.
We demonstrate how two straightforward simplifications to the state-of-the-art RL algorithm PI2 suffice to convert it into the black-box optimization algorithm (\mu_W,\lambda)-ES. Furthermore, we show that (\mu_W,\lambda)-ES empirically outperforms PI2 on several tasks. It is striking that PI2 and (\mu_W,\lambda)-ES share a common core, and that the simpler, older algorithm outperforms the more sophisticated, newer one.
We argue that this is due to a third trend in robot skill learning: the predominant use of dynamic movement primitives (DMPs). We show how DMPs dramatically simplify the learning problem, and discuss the implications of this for past and future work on robot skill learning. },
bib2html_pubtype = {Journal},
bib2html_rescat = {Reinforcement Learning of Robot Skills}
}