Emergent Cooperation under Uncertain Incentive Alignment

TL;DR

This paper investigates how cooperation emerges among reinforcement learning agents in uncertain, sparse interaction environments with mixed incentives, highlighting the roles of reputation and intrinsic rewards in fostering cooperation.

Contribution

It introduces an analysis of cooperation under incentive uncertainty and evaluates mechanisms like reputation and intrinsic rewards in diverse incentive scenarios.

Findings

Uncertainty reduces agents' ability to cooperate optimally.

Reputation mechanisms improve cooperation in mixed-motive settings.

Intrinsic rewards enhance cooperative behavior across environments.

Abstract

Understanding the emergence of cooperation in systems of computational agents is crucial for the development of effective cooperative AI. Interaction among individuals in real-world settings are often sparse and occur within a broad spectrum of incentives, which often are only partially known. In this work, we explore how cooperation can arise among reinforcement learning agents in scenarios characterised by infrequent encounters, and where agents face uncertainty about the alignment of their incentives with those of others. To do so, we train the agents under a wide spectrum of environments ranging from fully competitive, to fully cooperative, to mixed-motives. Under this type of uncertainty we study the effects of mechanisms, such as reputation and intrinsic rewards, that have been proposed in the literature to foster cooperation in mixed-motives environments. Our findings show that uncertainty substantially lowers the agents' ability to engage in cooperative behaviour, when that would be the best course of action. In this scenario, the use of effective reputation mechanisms and intrinsic rewards boosts the agents' capability to act nearly-optimally in cooperative environments, while greatly enhancing cooperation in mixed-motive environments as well.