arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.04788cs.AIcs.MA
收藏

多Agent MDP的可扩展随时规划

Scalable Anytime Planning for Multi-Agent MDPs

Stanford University(斯坦福大学);Microsoft(微软)

Shushman Choudhury, Jayesh K. Gupta, Peter Morales, Mykel J. Kochenderfer

摘要:

我们提出了一个可扩展的树搜索规划算法的大型多智能体顺序决策问题,需要动态协作。代理团队需要在许多领域协调决策,但由于联合行动空间随代理数量的指数增长,幼稚的方法会失败。我们规避这种复杂性,通过一个随时随地的方法,使我们能够交易计算近似质量,并动态协调行动。我们的算法包括三个要素:在线规划与蒙特卡罗树搜索(MCTS),因子表示的本地代理与协调图的相互作用,和迭代最大加联合行动选择的方法。我们评估我们的方法在基准SysAdmin域与静态协调图,并实现可比的性能与低得多的计算成本比我们的MCTS基线。我们还介绍了一个多无人机交付域与动态,即,状态相关的协调图,并展示了我们的方法如何扩展到这个领域的大问题,是其他MCTS方法难以解决。我们在https://github.com/JuliaPOMDP/FactoredValueMCTS.jl上提供了我们算法的开源实现。

英文摘要:

We present a scalable tree search planning algorithm for large multi-agent sequential decision problems that require dynamic collaboration. Teams of agents need to coordinate decisions in many domains, but naive approaches fail due to the exponential growth of the joint action space with the number of agents. We circumvent this complexity through an anytime approach that allows us to trade computation for approximation quality and also dynamically coordinate actions. Our algorithm comprises three elements: online planning with Monte Carlo Tree Search (MCTS), factored representations of local agent interactions with coordination graphs, and the iterative Max-Plus method for joint action selection. We evaluate our approach on the benchmark SysAdmin domain with static coordination graphs and achieve comparable performance with much lower computation cost than our MCTS baselines. We also introduce a multi-drone delivery domain with dynamic, i.e., state-dependent coordination graphs, and demonstrate how our approach scales to large problems on this domain that are intractable for other MCTS methods. We provide an open-source implementation of our algorithm at https://github.com/JuliaPOMDP/FactoredValueMCTS.jl.

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。

↑