Show simple item record

A Distributed Algorithm for Solving a Class of Multi-agent Markov Decision Problems

dc.contributor.advisorFu, Michael C.en_US
dc.contributor.authorChang, Hyeong Sooen_US
dc.contributor.authorFu, Michael C.en_US
dc.description.abstractWe consider a class of infinite horizon Markov decision processes (MDPs) with multiple decision makers, called agents,and a general joint reward structure, but a special decomposable state/action structure such that each individual agent's actions affect the system's state transitions independently from the actions of all other agents. We introduce the concept of ``localization," where each agent need only consider a ``local" MDP defined on its own state and action spaces. Based on this localization concept, we propose an iterative distributed algorithm that emulates gradient ascent and which converges to a locally optimal solution for the average reward case. The solution is an ``autonomous" joint policy such that each agent's action is based on only its local state. Finally, we discuss the implication of the localization concept for discounted reward problems.en_US
dc.format.extent195556 bytes
dc.relation.ispartofseriesISR; TR 2003-25en_US
dc.titleA Distributed Algorithm for Solving a Class of Multi-agent Markov Decision Problemsen_US
dc.typeTechnical Reporten_US

Files in this item


This item appears in the following Collection(s)

Show simple item record