Model-based direct policy search

Jan Hendrik Metzen, Frank Kirchner

In: Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems. International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS-10) May 10-14 Toronto Ontario Canada Seiten 1589-1590 ISBN 978-0-9826571-1-9 5/2010.


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.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence