2022
DOI: 10.3233/ia-210081
|View full text |Cite
|
Sign up to set email alerts
|

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

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 … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
2

Relationship

1
1

Authors

Journals

citations
Cited by 2 publications
(3 citation statements)
references
References 101 publications
0
3
0
Order By: Relevance
“…Deep learning models have also advanced the study of compositionality and generalization in EmCom , fostering multi-agent cooperation with the emergence of language ( Lazaridou et al, 2020 ), and allowing systems to form more complex messages ( Chaabouni et al, 2020 ; Rita et al, 2022b ; Xu et al, 2022 ). These contributions are thoroughly reviewed in ( Galke et al, 2022 ; Brandizzi, 2023 ), which offer an extensive overview of the strides made in this domain.…”
Section: Related Workmentioning
confidence: 99%
“…Deep learning models have also advanced the study of compositionality and generalization in EmCom , fostering multi-agent cooperation with the emergence of language ( Lazaridou et al, 2020 ), and allowing systems to form more complex messages ( Chaabouni et al, 2020 ; Rita et al, 2022b ; Xu et al, 2022 ). These contributions are thoroughly reviewed in ( Galke et al, 2022 ; Brandizzi, 2023 ), which offer an extensive overview of the strides made in this domain.…”
Section: Related Workmentioning
confidence: 99%
“…Unlike previous Communication-focused games, this second category utilizes communication as a means to achieve a goal different from the communicative act itself. The agents' action space includes both communication signals and other game-dependent actions, which range from physic simulators [48], [49], navigation tasks [26], [50]- [53], negotiation settings [54]- [56] to social deduction games [57]- [59]. These games aim to recreate the environment in which language emerged, emphasizing the view that human language did not emerge as a goal itself but rather as a means of coordinating actions between humans.…”
Section: B: Communication-assistedmentioning
confidence: 99%
“…Similarly, [58] set up a social deduction game 6 where agents must infer the trustworthiness of others through interactions and hard-coded communication actions. [57] also study this setup, but in a canonical EmCom environment without communication constraints. Despite highly adverse scenarios, such as incomplete information and strategic deception, the authors show that communicating agents can still defeat opponents through effective communication and collaboration.…”
Section: C: Competitionmentioning
confidence: 99%