Skip to main content Skip to main navigation

Publication

Model-based direct policy search

Jan Hendrik Metzen; Frank Kirchner
In: AAMAS '10: Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems - Volume 1. International Conference on Autonomous Agents and Multiagent Systems (AAMAS-10), May 10-14, Toronto, ON, Canada, Pages 1589-1590, ISBN 978-0-9826571-1-9, 5/2010.

Abstract

Scaling Reinforcement Learning (RL) to real-world problems with continuous state and action spaces remains a challenge. This is partly due to the reason that the optimal value function can become quite complex in continuous domains. In this paper, we propose to avoid learning the optimal value function at all but to use direct policy search methods in combination with model-based RL instead.