- Title
- Empirical evaluation methods for multiobjective reinforcement learning algorithms
- Creator
- Vamplew, Peter; Dazeley, Richard; Berry, Adam; Issabekov, Rustam; Dekker, Evan
- Date
- 2011
- Type
- Text; Journal article
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/68392
- Identifier
- vital:4103
- Identifier
-
https://doi.org/10.1007/s10994-010-5232-5
- Identifier
- ISSN:0885-6125
- Abstract
- While a number of algorithms for multiobjective reinforcement learning have been proposed, and a small number of applications developed, there has been very little rigorous empirical evaluation of the performance and limitations of these algorithms. This paper proposes standard methods for such empirical evaluation, to act as a foundation for future comparative studies. Two classes of multiobjective reinforcement learning algorithms are identified, and appropriate evaluation metrics and methodologies are proposed for each class. A suite of benchmark problems with known Pareto fronts is described, and future extensions and implementations of this benchmark suite are discussed. The utility of the proposed evaluation methods are demonstrated via an empirical comparison of two example learning algorithms. © 2010 The Author(s).
- Relation
- Machine Learning Vol. 84, no. 1-2 (2011), p. 51-80
- Rights
- Copyright Springerlink
- Rights
- This metadata is freely available under a CCO license
- Subject
- 0801 Artificial Intelligence and Image Processing; Empirical methods; Multiobjective reinforcement learning; Multiple objectives; Pareto fronts; Pareto optimal policies; Empirical method; Multi objective; Multiobjective optimization; Pareto principle; Reinforcement learning; Learning algorithms; 1702 Cognitive Science
- Reviewed
- Hits: 4597
- Visitors: 4418
- Downloads: 0
Thumbnail | File | Description | Size | Format |
---|