Competitive Safety Analysis: Robust Decision-Making in Multi-Agent Systems

TL;DR

This paper introduces competitive safety analysis, a method for robust decision-making in multi-agent systems that guarantees certain payoffs and is applicable to various settings including load balancing and auctions.

Contribution

It proposes the concept of safety level and competitive safety strategies, bridging normative AI and equilibrium analysis, with guarantees in classical and decentralized multi-agent scenarios.

Findings

Safety level strategies guarantee Nash equilibrium payoffs.

In large agent systems, expected payoff can reach 8/9 of Nash equilibrium.

Applicable to load balancing, communication networks, and auctions.

Abstract

Much work in AI deals with the selection of proper actions in a given (known or unknown) environment. However, the way to select a proper action when facing other agents is quite unclear. Most work in AI adopts classical game-theoretic equilibrium analysis to predict agent behavior in such settings. This approach however does not provide us with any guarantee for the agent. In this paper we introduce competitive safety analysis. This approach bridges the gap between the desired normative AI approach, where a strategy should be selected in order to guarantee a desired payoff, and equilibrium analysis. We show that a safety level strategy is able to guarantee the value obtained in a Nash equilibrium, in several classical computer science settings. Then, we discuss the concept of competitive safety strategies, and illustrate its use in a decentralized load balancing setting, typical to network problems. In particular, we show that when we have many agents, it is possible to guarantee an expected payoff which is a factor of 8/9 of the payoff obtained in a Nash equilibrium. Our discussion of competitive safety analysis for decentralized load balancing is further developed to deal with many communication links and arbitrary speeds. Finally, we discuss the extension of the above concepts to Bayesian games, and illustrate their use in a basic auctions setup.