Dynamic Programming Approximations for Partially Observable Stochastic Games

• Main Authors: KUMAR, Akshat, ZILBERSTEIN, Shlomo
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2009
• Subjects: Artificial Intelligence and Robotics; Operations Research, Systems Engineering and Industrial Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/2214; https://ink.library.smu.edu.sg/context/sis_research/article/3214/viewcontent/KZflairs09.pdf
• Institution: Singapore Management University

Partially observable stochastic games (POSGs) provide a rich mathematical framework for planning under uncertainty by a group of agents. However, this modeling advantage comes with a price, namely a high computational cost. Solving POSGs optimally quickly becomes intractable after a few decision cycles. Our main contribution is to provide bounded approximation techniques, which enable us to scale POSG algorithms by several orders of magnitude. We study both the POSG model and its cooperative counterpart, DEC-POMDP. Experiments on a number of problems confirm the scalability of our approach while still providing useful policies.