RLupus: Cooperation through emergent communication in The Werewolf social deduction game

Author:

Brandizzi Nicolo’1,Grossi Davide23,Iocchi Luca1

Affiliation:

1. Dipartimento di Ingegneria Informatica, Automatica e Gestionale, Sapienza University of Rome, Italy

2. Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands

3. Amsterdam Center for Law and Economics and Institute for Logic, Language and Computation, University of Amsterdam, The Netherlands

Abstract

This paper focuses on the emergence of communication to support cooperation in environments modeled as social deduction games (SDG), that are games where players communicate freely to deduce each others’ hidden intentions. We first state the problem by giving a general formalization of SDG and a possible solution framework based on reinforcement learning. Next, we focus on a specific SDG, known as The Werewolf, and study if and how various forms of communication influence the outcome of the game. Experimental results show that introducing a communication signal greatly increases the winning chances of a class of players. We also study the effect of the signal’s length and range on the overall performance showing a non-linear relationship.

Publisher

IOS Press

Subject

Artificial Intelligence

Reference56 articles.

1. Social games in a social network;Abramson;Physical Review E,2001

2. Ahmed Z. , Roux N.L. , Norouzi M. and Schuurmans D. , Understanding the impact of entropy on policy optimization. In ChaudhuriK. and Salakhut-dinovR., editors, Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, volume 97 of Proceedings of Machine Learning Research, pages 151–160. PMLR, 2019.

3. Baker B. , Kanitscheider I. , Markov T.M. , Wu Y. , Powell G. , McGrew B. and Mordatch I. , Emergent tool use from multi-agent autocurricula, In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, OpenReview.net, (2020).

4. A neural probabilistic language model;Bengio;The Journal of Machine Learning Research,2003

5. Bi X. and Tanaka T. , Human-side strategies in the werewolf game against the stealth werewolf strategy, In International Conference on Computers and Games, pages 93–102. Springer, (2016).

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3