A Generic Agent Architecture for Cooperative Multi-Agent Games

Abstract

The goal of this dissertation is to develop a high level generic architecture for the development of agents able to effectively play gameswith strong social components and a mix of competition and cooperation. Traditional techniques used in the context of games include searchingstrategies like Branch & Bound as well as Monte-Carlo approaches, however, these techniques are difficult to apply to this category of games,due to the often enormous search trees and the difficulty in calculating the value of a player's position or move.We propose a generic agent architecture that tackles the subjects of negotiation, trust and opponent modelling, simplifying the development ofagents capable of playing these games effectively. This architecture is split into four independent modules, taking inspiration from thestructure of a wartime nation, the President, the Strategic Office, the Foreign Office and the Intelligence Office.We demonstrate the applications of this architecture by instantiating it using two different games, Diplomacy and Werewolves of Miller's Hollow,and testing the obtained agents in a variety of scenarios against existing agents. The results obtained show that the architecture is genericenough to be applied in a wide variety of games, and the inclusion of negotiation, trust and opponent modelling allows for more effective agents.