论文标题
多目标动态编程，精度有限
Multi-objective dynamic programming with limited precision
论文作者
论文摘要
本文解决了近似多目标马尔可夫决策过程的所有解决方案集的问题。我们表明，在绝大多数有趣的情况下，解决方案的数量是指数级甚至是无限的。为了克服这一困难，我们建议通过基于White的多目标值动态编程算法的有限精确方法近似所有解决方案的集合。我们证明了计算的溶液的数量是可以处理的，并通过实验表明获得的解决方案是真实帕累托前部的良好近似值。
This paper addresses the problem of approximating the set of all solutions for Multi-objective Markov Decision Processes. We show that in the vast majority of interesting cases, the number of solutions is exponential or even infinite. In order to overcome this difficulty we propose to approximate the set of all solutions by means of a limited precision approach based on White's multi-objective value-iteration dynamic programming algorithm. We prove that the number of calculated solutions is tractable and show experimentally that the solutions obtained are a good approximation of the true Pareto front.
