Werewolf Game Modeling Using Action Probabilities Based on Play Log Analysis

Hirata, Yoshihiro; Inaba, Michimasa; Takahashi, Keníchi; Toriumi, Fujio; Osawa, Hirotaka; Katagami, Daisuke; Shinoda, Keiko

doi:10.1007/978-3-319-50935-8_10

Cited by 10 publications

(9 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We adopt PDA in Werewolf game [10], that can adjust its contents in the way that increases the player's dominant power and hence promotes selfefficacy and gameplay experience of the player. In this section, we describe a pilot study to test the PDA concept using a digital Werewolf game [41], to evaluate the psychology effects, self-efficacy in this study, between PDA and UX.…”

Section: Pilot Study On a Social Deduction Gamementioning

confidence: 99%

Player Dominance Adjustment in Games

Xu¹

2021

Preprint

View full text Add to dashboard Cite

Player Dominance Adjustment in GamesAbove all, I would like to thank my research supervisor, Prof. Ruck Thawonmas, who has supported me in all my endeavors and provided guidance, encouragement, and suggestion, gave me such many chances to publish papers in conferences organized in domestic or oversea. I appreciate his kindness to give his time generously. Besides, he has provided many useful materials as well as created an environment for me where it is a pleasure to study and conduct research.I would like to express special thanks to Dr. Pujana Paliyawan, who is like my second supervisor. I started my undergraduate research in advance with him and learned a lot of things necessary for writing papers, conducting experiments, polishing ideas for research, etc.. They helped me in all of my research studies, the paper would not be finished perfectly without their advice. I truly appreciate their time and kindness.Thanks also to my girlfriend Chen, for providing me consistent encouragement and caring within four years of undergraduate study, not only accompanies me in those wonderful lives, but also provides guidance for me in daily life even my research when required. Her existence keeping me optimistic when facing all the obstacles in my study and life in Japan.Most importantly, I would also like to thank my parents for their love, support, and encouragement.Finally, Thanks to Ritsumeikan University and all the professors as well as lecturers who taught me in classes. I would never forget valuable experiences gained there for the instructions they gave.

show abstract

Section: Pilot Study On a Social Deduction Gamementioning

confidence: 99%

Player Dominance Adjustment in Games

Xu¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Compared to other AI benchmark games such as Go, Starcraft or Poker, Werewolf is unique in that the communication between agents is the key skill that must be mastered to obtain high levels of play. A successful Werewolf agent must be able to build a model of the other players' beliefs, identify allied players, and exchange this information through communication [13].…”

Section: The Werewolf Leaguementioning

confidence: 99%

Challenges and Main Results of the Automated Negotiating Agents Competition (ANAC) 2019

Aydoğan

Baarslag

Fujita

et al. 2020

Multi-Agent Systems and Agreement Technologies

Self Cite

View full text Add to dashboard Cite

The Automated Negotiating Agents Competition (ANAC) is a yearly-organized international contest in which participants from all over the world develop intelligent negotiating agents for a variety of negotiation problems. To facilitate the research on agent-based negotiation, the organizers introduce new research challenges every year. ANAC 2019 posed five negotiation challenges: automated negotiation with partial preferences, repeated human-agent negotiation, negotiation in supplychain management, negotiating in the strategic game of Diplomacy, and in the Werewolf game. This paper introduces the challenges and discusses the main findings and lessons learnt per league.

show abstract

“…Nakamura et al,(2016) reported that estimating player roles based multiple perspectives increased winning rate. Hirata et al,(2016) made an agent using action probabilities based on game logs of werewolf BBS for behaving like human beings. Their algorithms are not specialized in werewolf agent.…”

Section: Related Workmentioning

confidence: 99%

“…If an agent can talk and mislead villagers without attracting attention from other players, it is a strong stealth werewolf. Although there are previous studies that have investigated conversations in the Werewolf game (Hirata et al, 2016), they are not done so from the standpoint of the stealth werewolf. Therefore, in this paper, we investigate the influences of the numbers of utterances, appearances in utterances of other players, and whispers, on the victory or defeat of werewolves.…”

Section: Introductionmentioning

confidence: 99%

Strategies for an Autonomous Agent Playing the “Werewolf game” as a Stealth Werewolf

Shoji¹,

Jotaro²,

Kosuke³

et al. 2019

Proceedings of the 1st International Workshop of AI Werewolf and Dialog System ({AIWolfDial2019})

View full text Add to dashboard Cite

The "Werewolf game" is a popular multiplayer game wherein "villagers" try to figure out who is a "werewolf" through conversations. Werewolves usually pretend to be villagers. In this paper, we studied conversations in game logs in order to investigate how werewolves' cooperation contributed to increasing the winning percentage of the werewolves' team. As the number of "whispers" that are utterances via werewolves' private chat may be regarded as a measure of the werewolves' cooperation, we investigated the relation between the number of whispers and the winning percentage. As the result, we observed that the winning percentage of werewolves' team increased by 63 points at most when the number of whispers of at least two werewolves was more than 106.

show abstract

Werewolf Game Modeling Using Action Probabilities Based on Play Log Analysis

Cited by 10 publications

References 12 publications

Player Dominance Adjustment in Games

Player Dominance Adjustment in Games

Challenges and Main Results of the Automated Negotiating Agents Competition (ANAC) 2019

Strategies for an Autonomous Agent Playing the “Werewolf game” as a Stealth Werewolf

Contact Info

Product

Resources

About