Learning in Multi-Objective Public Goods Games with Non-Linear Utilities
This work addresses incentive alignment in collaborative AI agents for scenarios like resource allocation, but it is incremental as it extends existing game theory models with new utility functions.
The paper tackles the problem of optimal decision-making under risk and uncertainty in multi-objective Public Goods Games by introducing a parametric non-linear utility function to model agent risk preferences, and it demonstrates how different preference and uncertainty combinations can sustain cooperative or competitive patterns in varying environments.
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).