Learning to Resolve Alliance Dilemmas in Many-Player Zero-Sum Games

02/27/2020
by   Edward Hughes, et al.
0

Zero-sum games have long guided artificial intelligence research, since they possess both a rich strategy space of best-responses and a clear evaluation metric. What's more, competition is a vital mechanism in many real-world multi-agent systems capable of generating intelligent innovations: Darwinian evolution, the market economy and the AlphaZero algorithm, to name a few. In two-player zero-sum games, the challenge is usually viewed as finding Nash equilibrium strategies, safeguarding against exploitation regardless of the opponent. While this captures the intricacies of chess or Go, it avoids the notion of cooperation with co-players, a hallmark of the major transitions leading from unicellular organisms to human civilization. Beyond two players, alliance formation often confers an advantage; however this requires trust, namely the promise of mutual cooperation in the face of incentives to defect. Successful play therefore requires adaptation to co-players rather than the pursuit of non-exploitability. Here we argue that a systematic study of many-player zero-sum games is a crucial element of artificial intelligence research. Using symmetric zero-sum matrix games, we demonstrate formally that alliance formation may be seen as a social dilemma, and empirically that naïve multi-agent reinforcement learning therefore fails to form alliances. We introduce a toy model of economic competition, and show how reinforcement learning may be augmented with a peer-to-peer contract mechanism to discover and enforce alliances. Finally, we generalize our agent model to incorporate temporally-extended contracts, presenting opportunities for further work.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/19/2022

Anytime PSRO for Two-Player Zero-Sum Games

Policy space response oracles (PSRO) is a multi-agent reinforcement lear...
research
10/10/2021

Reinforcement Learning In Two Player Zero Sum Simultaneous Action Games

Two player zero sum simultaneous action games are common in video games,...
research
03/06/2023

MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning

Open-ended learning methods that automatically generate a curriculum of ...
research
12/04/2021

Cooperation, Retaliation and Forgiveness in Revision Games

Revision game is a very new model formulating the situation where player...
research
07/16/2022

A Survey of Decision Making in Adversarial Games

Game theory has by now found numerous applications in various fields, in...
research
05/05/2022

General sum stochastic games with networked information flows

Inspired by applications such as supply chain management, epidemics, and...
research
10/31/2021

Adapting paths against zero-determinant strategies in repeated prisoner's dilemma games

Long-term cooperation, competition, or exploitation among individuals ca...

Please sign up or login with your details

Forgot password? Click here to reset