Learning in Multi-Objective Public Goods Games with Non-Linear Utilities

TL;DR

This paper explores how multi-objective reinforcement learning with non-linear utility functions influences decision-making and cooperation in Public Goods Games with diverse risk preferences and environmental uncertainties.

Contribution

It introduces a parametric non-linear utility model for risk preferences in multi-objective Public Goods Games and analyzes its impact on cooperative behavior under uncertainty.

Findings

Different preference combinations promote cooperation in competitive environments.

Environmental uncertainty affects incentive alignment and strategic outcomes.

Non-linear utility modeling influences emergence of cooperation and competition.

Abstract

Addressing the question of how to achieve optimal decision-making under risk and uncertainty is crucial for enhancing the capabilities of artificial agents that collaborate with or support humans. In this work, we address this question in the context of Public Goods Games. We study learning in a novel multi-objective version of the Public Goods Game where agents have different risk preferences, by means of multi-objective reinforcement learning. We introduce a parametric non-linear utility function to model risk preferences at the level of individual agents, over the collective and individual reward components of the game. We study the interplay between such preference modelling and environmental uncertainty on the incentive alignment level in the game. We demonstrate how different combinations of individual preferences and environmental uncertainties sustain the emergence of cooperative patterns in non-cooperative environments (i.e., where competitive strategies are dominant), while others sustain competitive patterns in cooperative environments (i.e., where cooperative strategies are dominant).