Solving multi-agent games on networks

Abstract

Multi-agent games on networks (GoNs) have nodes that represent agents and edges that represent interactions among agents. A special class of GoNs is composed of 2-players games on each of their edges. General GoNs have games that are played by all agents in each neighborhood. Solutions to games on networks are stable states (i.e., pure Nash equilibria), and in general one is interested in efficient solutions (of high global social welfare). This study addresses the multi-agent aspect of games on networks—a system of multiple agents that compose a game and seek a solution by performing a multi-agent (distributed) algorithm. The agents playing the game are assumed to be strategic and an iterative distributed algorithm is proposed, that lets the agents interact (i.e., negotiate) in neighborhoods in a process that guarantees the convergence of any multi-agent game on network to a globally stable state. The proposed algorithm—the TECon algorithm—iterates, one neighborhood at a time, performing a repeated social choice action. A truth-enforcing mechanism is integrated into the algorithm, collecting the valuations of agents in each neighborhood and computing incentives while eliminating strategic behavior. The proposed method is proven to converge to globally stable states that are at least as efficient as the initial state, for any game on network. A specific version of the algorithm is given for the class of Public Goods Games, where the main properties of the algorithm are guaranteed even when the strategic agents playing the game consider their possible future valuations when interacting. An extensive experimental evaluation on randomly generated games on networks demonstrates that the TECon algorithm converges very rapidly. On general forms of public goods games, the proposed algorithm outperforms former solving methods, where former methods are applicable.