Inequity aversion improves cooperation in intertemporal social dilemmas

TL;DR

This paper demonstrates that incorporating inequity aversion into multi-agent reinforcement learning enhances cooperation in complex, temporally extended social dilemmas, especially by improving temporal credit assignment.

Contribution

It extends inequity aversion concepts to Markov games, showing it promotes cooperation and improves learning in intertemporal social dilemmas.

Findings

Inequity aversion promotes cooperation in Markov games.

It enhances temporal credit assignment in social dilemmas.

Results help explain emergence of large-scale cooperation.

Abstract

Groups of humans are often able to find ways to cooperate with one another in complex, temporally extended social dilemmas. Models based on behavioral economics are only able to explain this phenomenon for unrealistic stateless matrix games. Recently, multi-agent reinforcement learning has been applied to generalize social dilemma problems to temporally and spatially extended Markov games. However, this has not yet generated an agent that learns to cooperate in social dilemmas as humans do. A key insight is that many, but not all, human individuals have inequity averse social preferences. This promotes a particular resolution of the matrix game social dilemma wherein inequity-averse individuals are personally pro-social and punish defectors. Here we extend this idea to Markov games and show that it promotes cooperation in several types of sequential social dilemma, via a profitable interaction with policy learnability. In particular, we find that inequity aversion improves temporal credit assignment for the important class of intertemporal social dilemmas. These results help explain how large-scale cooperation may emerge and persist.