Constructing stochastic mixture policies for episodic multiobjective reinforcement learning tasks

- Vamplew, Peter, Dazeley, Richard, Barker, Ewan, Kelarev, Andrei

Title
Constructing stochastic mixture policies for episodic multiobjective reinforcement learning tasks
Creator
Vamplew, Peter; Dazeley, Richard; Barker, Ewan; Kelarev, Andrei
Date
2009
Type
Text; Book chapter
Identifier
http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/67587
Identifier
vital:3298
Identifier
https://doi.org/10.1007/978-3-642-10439-8_35
Identifier
ISBN:978-3-642-10438-1
Abstract
Multiobjective reinforcement learning algorithms extend reinforcement learning techniques to problems with multiple conflicting objectives. This paper discusses the advantages gained from applying stochastic policies to multiobjective tasks and examines a particular form of stochastic policy known as a mixture policy. Two methods are proposed for deriving mixture policies for episodic multiobjective tasks from deterministic base policies found via scalarised reinforcement learning. It is shown that these approaches are an efficient means of identifying solutions which offer a superior match to the user’s preferences than can be achieved by methods based strictly on deterministic policies.
Publisher
Heidelberg, Germany Springer
Relation
AI 2009 : Advances in Artificial Intelligence : 22nd Australasian Joint Conference, Melbourne, Australia, December 1-4, 2009. Proceedings Chapter p. 340-349
Rights
Copyright Springer
Rights
Open Access
Rights
This metadata is freely available under a CCO license
Subject
Multiobjective; Reinforcement learning; Scalarisation; Pareto fronts
Full Text
  • Hits: 2510
  • Visitors: 2853
  • Downloads: 453
Thumbnail File Description Size Format
SOURCE1 Accepted version 80 KB Adobe Acrobat PDF