arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1104.5601cs.LGcs.AI
收藏

马尔可夫决策过程的均值-方差优化

Mean-Variance Optimization in Markov Decision Processes

Technion(以色列理工学院);Massachusetts Institute of Technology(麻省理工学院)

Shie Mannor, John Tsitsiklis

摘要:

我们考虑有限时域马尔可夫决策过程下的性能指标,涉及的平均值和方差的累积奖励。我们发现,无论是随机或基于历史的政策可以提高性能。我们证明了在方差约束下最大化平均报酬的策略的计算复杂性在某些情况下是NP困难的,而在其他情况下是强NP困难的。最后给出了伪多项式精确算法和近似算法。

英文摘要:

We consider finite horizon Markov decision processes under performance measures that involve both the mean and the variance of the cumulative reward. We show that either randomized or history-based policies can improve performance. We prove that the complexity of computing a policy that maximizes the mean reward under a variance constraint is NP-hard for some cases, and strongly NP-hard for others. We finally offer pseudopolynomial exact and approximation algorithms.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑