Lifting in Multi-agent Systems under Uncertainty

Tanya Braun, Marcel Gehrke, Florian Lau, Ralf Möller

Keywords: lifting, statistical relational AI, multi-agent system under symmetries

TL;DR: A fusion of lifting and multi-agent systems allowing for tractability in agent numbers and finding how many agents are needed

Abstract: A decentralised partially observable Markov decision problem (DecPOMDP) formalises collaborative multi-agent decision making. A solution to a DecPOMDP is a joint policy for the agents, fulfilling an optimality criterion such as maximum expected utility. A crux is that the problem is intractable regarding the number of agents. Inspired by lifted inference, this paper examines symmetries within the agent set for a potential tractability. Specifically, this paper contributes (i) specifications of counting and isomorphic symmetries, (ii) a compact encoding of symmetric DecPOMDPs as partitioned DecPOMDPs, and (iii) a formal analysis of complexity and tractability. This works allows tractability in terms of agent numbers and a new query type for isomorphic DecPOMDPs.