Consequentialist conditional cooperation in social dilemmas with imperfect information

TL;DR

This paper introduces consequentialist conditional cooperation strategies in social dilemmas with imperfect information, using deep reinforcement learning to promote cooperation and prevent exploitation in multi-agent interactions.

Contribution

It presents a novel class of strategies based solely on outcomes, demonstrating their effectiveness in complex social dilemmas through analytical and experimental methods.

Findings

Strategies conditioned on outcomes promote cooperation.

Deep RL can effectively implement these strategies.

Limitations highlight the importance of understanding intentions.

Abstract

Social dilemmas, where mutual cooperation can lead to high payoffs but participants face incentives to cheat, are ubiquitous in multi-agent interaction. We wish to construct agents that cooperate with pure cooperators, avoid exploitation by pure defectors, and incentivize cooperation from the rest. However, often the actions taken by a partner are (partially) unobserved or the consequences of individual actions are hard to predict. We show that in a large class of games good strategies can be constructed by conditioning one's behavior solely on outcomes (ie. one's past rewards). We call this consequentialist conditional cooperation. We show how to construct such strategies using deep reinforcement learning techniques and demonstrate, both analytically and experimentally, that they are effective in social dilemmas beyond simple matrix games. We also show the limitations of relying purely on consequences and discuss the need for understanding both the consequences of and the intentions behind an action.