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, (AAMAS-10), 10.5.-14.5.2010, Toronto, ON, o.A., pages 1589-1590, May/2010. ISBN: 978-0-9826571-1-9.
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.
Keywords
:
Direct policy search, model-based learning, reinforcement learning
