期刊
MACHINE LEARNING
卷 84, 期 1-2, 页码 51-80出版社
SPRINGER
DOI: 10.1007/s10994-010-5232-5
关键词
Multiobjective reinforcement learning; Multiple objectives; Empirical methods; Pareto fronts; Pareto optimal policies
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据