arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1206.6879cs.AI
收藏

一阶MDP的实用线性值逼近技术

Practical Linear Value-approximation Techniques for First-order MDPs

University of Toronto(多伦多大学)

Scott Sanner, Craig Boutilier

摘要:

一阶马尔可夫决策过程(FOMDPs)的近似线性规划(ALP)技术最近的工作表示价值函数线性w.r.t.一组一阶基函数,并使用线性编程技术来确定合适的权重。这种方法提供的优点是,它不需要简化的一阶价值函数,并允许一个解决FOMDPs独立于一个特定的域实例。在本文中,我们解决了几个问题,以提高这项工作的适用性:(1)我们可以扩展一阶ALP框架近似的政策迭代,以解决以前的方法的性能缺陷?(2)我们能自动生成基函数并评估它们对价值函数质量的影响吗?(3)我们怎样才能将具有普遍量化奖励的棘手问题分解为易于处理的子问题?我们提出了一些新的优化这些问题的答案,并提供了一个比较实证评估的物流问题,从ICAPS 2004年的概率规划比赛。

英文摘要:

Recent work on approximate linear programming (ALP) techniques for first-order Markov Decision Processes (FOMDPs) represents the value function linearly w.r.t. a set of first-order basis functions and uses linear programming techniques to determine suitable weights. This approach offers the advantage that it does not require simplification of the first-order value function, and allows one to solve FOMDPs independent of a specific domain instantiation. In this paper, we address several questions to enhance the applicability of this work: (1) Can we extend the first-order ALP framework to approximate policy iteration to address performance deficiencies of previous approaches? (2) Can we automatically generate basis functions and evaluate their impact on value function quality? (3) How can we decompose intractable problems with universally quantified rewards into tractable subproblems? We propose answers to these questions along with a number of novel optimizations and provide a comparative empirical evaluation on logistics problems from the ICAPS 2004 Probabilistic Planning Competition.

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。

↑