Grounded Predictions of Teamwork as a One-Shot Game: A Multiagent Multi-Armed Bandits Approach

TL;DR

This paper models teamwork among rational agents as a one-shot game and uses multi-armed bandits to learn equilibria, revealing insights into voluntary collaboration dynamics and human-like behaviors.

Contribution

It introduces a novel one-shot aggregative game framework for teamwork and develops a multiagent bandit system to approximate Nash equilibria in this context.

Findings

Agents exhibit human-like collaboration behaviors.

Team heterogeneity influences cooperation strategies.

Incentive systems impact team outcomes significantly.

Abstract

Humans possess innate collaborative capacities. However, effective teamwork often remains challenging. This study delves into the feasibility of collaboration within teams of rational, self-interested agents who engage in teamwork without the obligation to contribute. Drawing from psychological and game theoretical frameworks, we formalise teamwork as a one-shot aggregative game, integrating insights from Steiner's theory of group productivity. We characterise this novel game's Nash equilibria and propose a multiagent multi-armed bandit system that learns to converge to approximations of such equilibria. Our research contributes value to the areas of game theory and multiagent systems, paving the way for a better understanding of voluntary collaborative dynamics. We examine how team heterogeneity, task typology, and assessment difficulty influence agents' strategies and resulting teamwork outcomes. Finally, we empirically study the behaviour of work teams under incentive systems that defy analytical treatment. Our agents demonstrate human-like behaviour patterns, corroborating findings from social psychology research.