Automated Generation of Interaction Graphs for Value-Factored Decentralized POMDPs

• Main Authors: YEOH, William, KUMAR, Akshat, Zilberstein, Shlomo
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2013
• Subjects: Artificial Intelligence and Robotics; Computer Sciences
• Online Access: https://ink.library.smu.edu.sg/sis_research/2200; https://ink.library.smu.edu.sg/context/sis_research/article/3200/viewcontent/Automated_Generation_of_Interaction_Graphs_for_Value_Factored.pdf
• Institution: Singapore Management University

The Decentralized Partially Observable Markov Decision Process (Dec-POMDP) is a powerful model for multi-agent planning under uncertainty, but its applicability is hindered by its high complexity – solving Dec-POMDPs optimally is NEXP-hard. Recently, Kumar et al. introduced the Value Factorization (...