arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1011.0397cs.GTcs.SYeess.SYmath.OC
收藏

马尔可夫博弈最优控制的高效近似

Efficient Approximation of Optimal Control for Markov Games

University of Liverpool(利物浦大学);Universität des Saarlandes(萨尔兰大学);Technical University of Denmark(丹麦技术大学)

John Fearnley, Markus Rabe, Sven Schewe, Lijun Zhang

AI总结:

针对连续时间马尔可夫决策过程与博弈的有界时间可达性问题,提出一系列高阶精度近似方法(O(ε^3)、O(ε^4)、O(ε^5)),大幅减少离散区间数量,在CTMDP上性能可比启发式方法,在CTMG上首次实现实用算法,并给出位置策略。

摘要:

我们研究连续时间马尔可夫决策过程(CTMDP)和博弈(CTMG)的有界时间可达性问题。现有技术使用离散化方法将时间划分为离散区间,并分别近似每个区间的最优控制。当前技术在每个区间上提供O(ε^2)的精度,导致区间数量过大。我们提出一系列近似,实现O(ε^3)、O(ε^4)和O(ε^5)的精度,从而大幅减少考虑的区间数量。对于CTMDP,所得算法的性能与Buckholz和Schulz的启发式方法相当,同时具有理论保证。我们的所有结果都推广到CTMG,为这一问题首次提供了实际可实现的算法。我们还为两个玩家提供了位置策略,实现类似的误差界。

英文摘要:

We study the time-bounded reachability problem for continuous-time Markov decision processes (CTMDPs) and games (CTMGs). Existing techniques for this problem use discretisation techniques to break time into discrete intervals, and optimal control is approximated for each interval separately. Current techniques provide an accuracy of O(ε^2) on each interval, which leads to an infeasibly large number of intervals. We propose a sequence of approximations that achieve accuracies of O(ε^3), O(ε^4), and O(ε^5), that allow us to drastically reduce the number of intervals that are considered. For CTMDPs, the performance of the resulting algorithms is comparable to the heuristic approach given by Buckholz and Schulz, while also being theoretically justified. All of our results generalise to CTMGs, where our results yield the first practically implementable algorithms for this problem. We also provide positional strategies for both players that achieve similar error bounds.

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。

↑