Diverse agents for Ad-Hoc cooperation in Hanabi

Rodrigo Canaan; Julian Togelius; Andy Nealen; Stefan Menzel

doi:10.1109/CIG.2019.8847944

Diverse agents for Ad-Hoc cooperation in Hanabi

Rodrigo Canaan, Julian Togelius, Andy Nealen, Stefan Menzel

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In complex scenarios where a model of other actors is necessary to predict and interpret their actions, it is often desirable that the model works well with a wide variety of previously unknown actors. Hanabi is a card game that brings the problem of modeling other players to the forefront, but there is no agreement on how to best generate a pool of agents to use as partners in ad-hoc cooperation evaluation. This paper proposes Quality Diversity algorithms as a promising class of algorithms to generate populations for this purpose and shows an initial implementation of an agent generator based on this idea. We also discuss what metrics can be used to compare such generators, and how the proposed generator could be leveraged to help build adaptive agents for the game.

Original language	English (US)
Title of host publication	IEEE Conference on Games 2019, CoG 2019
Publisher	IEEE Computer Society
ISBN (Electronic)	9781728118840
DOIs	https://doi.org/10.1109/CIG.2019.8847944
State	Published - Aug 2019
Event	2019 IEEE Conference on Games, CoG 2019 - London, United Kingdom Duration: Aug 20 2019 → Aug 23 2019

Publication series

Name	IEEE Conference on Computatonal Intelligence and Games, CIG
Volume	2019-August
ISSN (Print)	2325-4270
ISSN (Electronic)	2325-4289

Conference

Conference	2019 IEEE Conference on Games, CoG 2019
Country/Territory	United Kingdom
City	London
Period	8/20/19 → 8/23/19

ASJC Scopus subject areas

Artificial Intelligence
Computer Graphics and Computer-Aided Design
Computer Vision and Pattern Recognition
Human-Computer Interaction
Software

Access to Document

10.1109/CIG.2019.8847944

Cite this

Canaan, R, Togelius, J, Nealen, A & Menzel, S 2019, Diverse agents for Ad-Hoc cooperation in Hanabi. in IEEE Conference on Games 2019, CoG 2019., 8847944, IEEE Conference on Computatonal Intelligence and Games, CIG, vol. 2019-August, IEEE Computer Society, 2019 IEEE Conference on Games, CoG 2019, London, United Kingdom, 8/20/19. https://doi.org/10.1109/CIG.2019.8847944

@inproceedings{0408ee8eb0fe4d14b214c4916f2070fc,

title = "Diverse agents for Ad-Hoc cooperation in Hanabi",

abstract = "In complex scenarios where a model of other actors is necessary to predict and interpret their actions, it is often desirable that the model works well with a wide variety of previously unknown actors. Hanabi is a card game that brings the problem of modeling other players to the forefront, but there is no agreement on how to best generate a pool of agents to use as partners in ad-hoc cooperation evaluation. This paper proposes Quality Diversity algorithms as a promising class of algorithms to generate populations for this purpose and shows an initial implementation of an agent generator based on this idea. We also discuss what metrics can be used to compare such generators, and how the proposed generator could be leveraged to help build adaptive agents for the game.",

author = "Rodrigo Canaan and Julian Togelius and Andy Nealen and Stefan Menzel",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE Conference on Games, CoG 2019 ; Conference date: 20-08-2019 Through 23-08-2019",

year = "2019",

month = aug,

doi = "10.1109/CIG.2019.8847944",

language = "English (US)",

series = "IEEE Conference on Computatonal Intelligence and Games, CIG",

publisher = "IEEE Computer Society",

booktitle = "IEEE Conference on Games 2019, CoG 2019",

}

TY - GEN

T1 - Diverse agents for Ad-Hoc cooperation in Hanabi

AU - Canaan, Rodrigo

AU - Togelius, Julian

AU - Nealen, Andy

AU - Menzel, Stefan

PY - 2019/8

Y1 - 2019/8

N2 - In complex scenarios where a model of other actors is necessary to predict and interpret their actions, it is often desirable that the model works well with a wide variety of previously unknown actors. Hanabi is a card game that brings the problem of modeling other players to the forefront, but there is no agreement on how to best generate a pool of agents to use as partners in ad-hoc cooperation evaluation. This paper proposes Quality Diversity algorithms as a promising class of algorithms to generate populations for this purpose and shows an initial implementation of an agent generator based on this idea. We also discuss what metrics can be used to compare such generators, and how the proposed generator could be leveraged to help build adaptive agents for the game.

AB - In complex scenarios where a model of other actors is necessary to predict and interpret their actions, it is often desirable that the model works well with a wide variety of previously unknown actors. Hanabi is a card game that brings the problem of modeling other players to the forefront, but there is no agreement on how to best generate a pool of agents to use as partners in ad-hoc cooperation evaluation. This paper proposes Quality Diversity algorithms as a promising class of algorithms to generate populations for this purpose and shows an initial implementation of an agent generator based on this idea. We also discuss what metrics can be used to compare such generators, and how the proposed generator could be leveraged to help build adaptive agents for the game.

UR - http://www.scopus.com/inward/record.url?scp=85073098407&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073098407&partnerID=8YFLogxK

U2 - 10.1109/CIG.2019.8847944

DO - 10.1109/CIG.2019.8847944

M3 - Conference contribution

AN - SCOPUS:85073098407

T3 - IEEE Conference on Computatonal Intelligence and Games, CIG

BT - IEEE Conference on Games 2019, CoG 2019

PB - IEEE Computer Society

T2 - 2019 IEEE Conference on Games, CoG 2019

Y2 - 20 August 2019 through 23 August 2019

ER -

Diverse agents for Ad-Hoc cooperation in Hanabi

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this