arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1111.0065cs.AI
收藏

基于通信的分布式MDP分解机制

Communication-Based Decomposition Mechanisms for Decentralized MDPs

Samsung Telecom Research Israel(三星以色列电信研究院)

Claudia V. Goldman, Shlomo Zilberstein

摘要:

随机环境中的多智能体规划问题可以形式化地归结为一个分散的马尔可夫决策问题。许多现实生活中出现的分布式问题,在制造,多机器人协调和信息收集的情况下,可以使用这个框架形式化。然而,在一般情况下找到最优解是困难的,限制了最近开发的算法的适用性。本文提供了一个实用的方法来解决分散控制问题时,决策者之间的通信是可能的,但成本高。我们开发的概念,基于通信的机制,使我们能够分解成多个单代理问题的分散MDP。在这个框架中,被称为分散式半马尔可夫决策过程与直接通信(Dec-SMDP-Com),代理之间的通信分开操作。我们发现,找到一个最佳的机制是相当于最佳地解决了Dec-SMDP-Com。我们还提供了一个启发式搜索算法,收敛于最佳分解。将分解限制在某些特定类型的局部行为上,可以显著降低规划的复杂性。特别是,我们提出了一个多项式时间算法的情况下,个体代理执行面向目标的行为之间的通信。本文最后提出了一个额外的易于处理的算法,该算法可以引入人类知识,从而将整个问题减少到寻找最佳通信时间。实证结果表明,这些方法提供了良好的近似解。

英文摘要:

Multi-agent planning in stochastic environments can be framed formally as a decentralized Markov decision problem. Many real-life distributed problems that arise in manufacturing, multi-robot coordination and information gathering scenarios can be formalized using this framework. However, finding the optimal solution in the general case is hard, limiting the applicability of recently developed algorithms. This paper provides a practical approach for solving decentralized control problems when communication among the decision makers is possible, but costly. We develop the notion of communication-based mechanism that allows us to decompose a decentralized MDP into multiple single-agent problems. In this framework, referred to as decentralized semi-Markov decision process with direct communication (Dec-SMDP-Com), agents operate separately between communications. We show that finding an optimal mechanism is equivalent to solving optimally a Dec-SMDP-Com. We also provide a heuristic search algorithm that converges on the optimal decomposition. Restricting the decomposition to some specific types of local behaviors reduces significantly the complexity of planning. In particular, we present a polynomial-time algorithm for the case in which individual agents perform goal-oriented behaviors between communications. The paper concludes with an additional tractable algorithm that enables the introduction of human knowledge, thereby reducing the overall problem to finding the best time to communicate. Empirical results show that these approaches provide good approximate solutions.

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。

↑