Model-based direct policy search

Authors:
Jan Hendrik Metzen;Frank Kirchner
Affiliations:
University Bremen, Bremen, Germany;University Bremen, Bremen, Germany
Venue:
Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1 - Volume 1
Year:
2010

Citing 4
Cited 0

Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
R-max - a general polynomial time algorithm for near-optimal reinforcement learning

The Journal of Machine Learning Research
Completely Derandomized Self-Adaptation in Evolution Strategies

Evolutionary Computation
Model-based exploration in continuous state spaces

SARA'07 Proceedings of the 7th International conference on Abstraction, reformulation, and approximation

Quantified Score

Hi-index	0.00

Visualization

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.