Emergent Prosociality in Multi-Agent Games Through Gifting

Abstract

Coordination is often critical to forming prosocial behaviors -behaviors that increase the overall sum of rewards received by all agents in a multi-agent game. However, state of the art reinforcement learning algorithms often suffer from converging to socially less desirable equilibria when multiple equilibria exist. Previous works address this challenge with explicit reward shaping, which requires the strong assumption that agents can be forced to be prosocial. We propose using a less restrictive peer-rewarding mechanism, gifting, that guides the agents toward more socially desirable equilibria while allowing agents to remain selfish and decentralized. Gifting allows each agent to give some of their reward to other agents. We employ a theoretical framework that captures the benefit of gifting in converging to the prosocial equilibrium by characterizing the equilibria's basins of attraction in a dynamical system. With gifting, we demonstrate increased convergence of high risk, general-sum coordination games to the prosocial equilibrium both via numerical analysis and experiments.

The emergence of division of labour through decentralized social sanctioning

“…The environment resets in terms of its resources and recovery ability between generations. This model of social sanctioning is broadly compatible with other redistributive (zero-sum) sanctioning mechanisms in the reinforcement learning literature [40][41][42]. It differs from the purely destructive negative-sum social sanctioning schemes considered by Köster et al [43] and Vinitsky et al [44].…”