Maintaining cooperation in complex social dilemmas using deep reinforcement learning

TL;DR

This paper develops modified deep reinforcement learning agents that promote cooperation in complex social dilemmas, maintaining mutual cooperation through simple, understandable, and forgiving strategies, without requiring complex training procedures.

Contribution

It introduces a novel modification to reinforcement learning enabling agents to sustain cooperation in social dilemmas, applicable in environments like Atari without extra training complexity.

Findings

Agents maintain cooperation in Markov social dilemmas

Modified agents are simple, nice, provokable, and forgiving

The approach works in environments where good strategies exist in zero-sum settings

Abstract

Social dilemmas are situations where individuals face a temptation to increase their payoffs at a cost to total welfare. Building artificially intelligent agents that achieve good outcomes in these situations is important because many real world interactions include a tension between selfish interests and the welfare of others. We show how to modify modern reinforcement learning methods to construct agents that act in ways that are simple to understand, nice (begin by cooperating), provokable (try to avoid being exploited), and forgiving (try to return to mutual cooperation). We show both theoretically and experimentally that such agents can maintain cooperation in Markov social dilemmas. Our construction does not require training methods beyond a modification of self-play, thus if an environment is such that good strategies can be constructed in the zero-sum case (eg. Atari) then we can construct agents that solve social dilemmas in this environment.