Maintaining cooperation in complex social dilemmas using deep reinforcement learning

07/04/2017
by   Adam Lerer, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/14/2023

Mediated Multi-Agent Reinforcement Learning

The majority of Multi-Agent Reinforcement Learning (MARL) literature equ...
research
10/19/2017

Consequentialist conditional cooperation in social dilemmas with imperfect information

Social dilemmas, where mutual cooperation can lead to high payoffs but p...
research
06/26/2022

Tackling Asymmetric and Circular Sequential Social Dilemmas with Reinforcement Learning and Graph-based Tit-for-Tat

In many societal and industrial interactions, participants generally pre...
research
10/04/2022

Incentivising cooperation by rewarding the weakest member

Autonomous agents that act with each other on behalf of humans are becom...
research
11/10/2020

Emergent Reciprocity and Team Formation from Randomized Uncertain Social Preferences

Multi-agent reinforcement learning (MARL) has shown recent success in in...
research
06/05/2019

Escaping the State of Nature: A Hobbesian Approach to Cooperation in Multi-agent Reinforcement Learning

Cooperation is a phenomenon that has been widely studied across many dif...
research
06/14/2021

Targeted Data Acquisition for Evolving Negotiation Agents

Successful negotiators must learn how to balance optimizing for self-int...

Please sign up or login with your details

Forgot password? Click here to reset