|
Using Ensemble Techniques and Multi- Objectivization to Solve Reinforcement Learning Problems Host Publication: 21st European Conference on Artificial Intelligence Authors: T. Brys, M. Taylor and A. Nowé Publication Date: Aug. 2014 Number of Pages: 2
Abstract: Recent work on multi-objectivization has shown how a single-objective reinforcement learning problem can be turned into a multi-objective problem with correlated objectives, by providing multiple reward shaping functions. The information contained in these correlated objectives can be exploited to solve the base, single-objective problem faster and better, given techniques specifically aimed at handling such correlated objectives. In this paper, we identify ensemble techniques as a set of methods that is suitable to solve multi-objectivized reinforcement learning problems. We empirically demonstrate their use on the Pursuit domain.
|
