Existence of Multiagent Equilibria with Limited Agents

TL;DR

This paper investigates whether equilibria exist in multiagent systems when agents have limitations, introduces a formal framework for limited equilibria, and provides theoretical and empirical insights into their existence and learnability.

Contribution

It introduces a formal extension of equilibria for limited agents, provides conditions for their existence, and demonstrates feasibility through empirical results.

Findings

Counterexample showing non-existence of equilibria with limitations

Conditions under which equilibria with limitations exist

Empirical validation of learning with limitations

Abstract

Multiagent learning is a necessary yet challenging problem as multiagent systems become more prevalent and environments become more dynamic. Much of the groundbreaking work in this area draws on notable results from game theory, in particular, the concept of Nash equilibria. Learners that directly learn an equilibrium obviously rely on their existence. Learners that instead seek to play optimally with respect to the other players also depend upon equilibria since equilibria are fixed points for learning. From another perspective, agents with limitations are real and common. These may be undesired physical limitations as well as self-imposed rational limitations, such as abstraction and approximation techniques, used to make learning tractable. This article explores the interactions of these two important concepts: equilibria and limitations in learning. We introduce the question of whether equilibria continue to exist when agents have limitations. We look at the general effects limitations can have on agent behavior, and define a natural extension of equilibria that accounts for these limitations. Using this formalization, we make three major contributions: (i) a counterexample for the general existence of equilibria with limitations, (ii) sufficient conditions on limitations that preserve their existence, (iii) three general classes of games and limitations that satisfy these conditions. We then present empirical results from a specific multiagent learning algorithm applied to a specific instance of limited agents. These results demonstrate that learning with limitations is feasible, when the conditions outlined by our theoretical analysis hold.