Probabilistic Inference Techniques for Scalable Multiagent Decision Making

• المؤلفون الرئيسيون: Akshat KUMAR, ZILBERSTEIN, Shlomo, TOUSSAINT, Marc
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2015
• الموضوعات: Artificial Intelligence and Robotics; Computer Sciences
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/3076; https://ink.library.smu.edu.sg/context/sis_research/article/4076/viewcontent/10944_Article_Text_20419_1_10_20180216.pdf

Decentralized POMDPs provide an expressive framework for multiagent sequential decision making. However, the complexity of these models---NEXP-Complete even for two agents---has limited their scalability. We present a promising new class of approximation algorithms by developing novel connections be...