Introduction: Invitation from a Game Master｜Artificial Intelligence based Werewolf
Artificial intelligence (AI), for which game play with humans has long been an important benchmark for research, can show the essence of intelligence and its requirements. AI has already defeated top-level human players in complete information games such as chess or Shogi. The complete information game Go currently has human players who can defeat the most advanced AI, but it seems only a matter of time before humans will be defeated by AI. In the field of incomplete games, Texas Hold’em Poker has a tradition of competition in the AI field. Real-time action video games are also spurring attempts at evaluating intelligence in real-time environments.
Compared to the previous game-related challenges, the communication or communicative intelligence skills that are commonly used in board games and card games have not been examined. When people play board games and card games, they converse with other players, and some games are advanced through conversation as so-called communication games. Few studies in the literature have analyzed artificial intelligence in relation to such communication games. “Are You a Werewolf?” is one of these communication games.
The Werewolf game is conducted solely through discussion and players must exert their cognitive faculties fully in order to win. In the game, players must hide information, in contrast to perfect information games such as chess or Reversi. Each player acquires secret information from other players’ conversations and behavior and acts by hiding information to accomplish their objectives. The game highlights various problems that have not been addressed adequately in the field of artificial intelligence, such as the asymmetric distribution of player information, the use of persuasion for earning confidence, and the use of speculation for detecting fabrications.
Following this, we started a project to create an “Artificial Intelligence Werewolf” (AIWolf) to play as the werewolf in place of a human player. The objective of this comprehensive project is not only to develop a game-playing algorithm, but also to develop virtual agents, real robots, and so on. To achieve this objective, there are a number of tasks that must be undertaken.
The collective intelligence approach is used for these tasks. To implement a collective intelligence approach, a common platform is indispensable. As described herein, we present the outline of a Werewolf platform for artificial intelligence (AI Wolf Platform), which has been developed as an open source project. We plan to hold an AI Wolf tournament in which researchers with various backgrounds can participate freely with the aim of realizing collective intelligence with the participants.
To achieve the above goals, we require research technologies in the following areas:
- Multi-agent simulation
- Machine learning
- Language processing
- Logic programming
- Human–agent interaction
- Cognitive science
Collaboration in these areas will be required for solving Werewolf. We anticipate that the development cycles will contribute to these fields and aid in the finding of essential features on social interaction.
Sorry, this entry is only available in Japanese.
We have presented the results of the Natural Language division in the INLG 2023 conference, as shown below. AIWolfDial 2023: Summary of Natural Language Division of 5th International AIWolf Contest. In Proceedings of The 16th International Natural Language Generation Conference (INLG 2023): Generation Challenges pp.84-98 (2023) https://aclanthology.org/2023.inlg-genchal.pdf Our presentation is shown in: https://sigdialinlg2023.github.io/paper_inlg136.html where slides … Continue reading Results of the 5th Int’l AIWolf Competition Natural Language Division
Results of Protocol Division Results of Infrastructure Division
Source Code for the finalist teams in the 5th International AIWolf Competition Protocol Division Team Name Source Code License Document pronto pronto.zip MIT pronto.pdf gotsumori Gotsumori.zip MIT Gotsumori.pdf ddhb ddhb.zip MIT ddhb.pdf ioh ioh.zip MIT ioh.pdf TOT TOT.zip Apache-2.0 TOT.pdf cash cash.zip MIT cash.pdf Lunatic Lunatic.zip MIT Lunatic.pdf mikami mikami.zip MIT mikami.pdf Howls03 Howls03.zip MIT … Continue reading 5th International AIWolf Competition Protocol Division — Source Code and Document
The finalists of protocol division are shown in the web page of protocol division.
You can download the game logs of the 4th international AIWolf contest final from here.
We have released AIWolf platform version 0.6.4. http://aiwolf.org/en/server/
Source Code for the finalist teams in the 4th International AIWolf Competition Protocol Division Team Name Source Code License Document Basket Basket.zip MIT Basket.pdf ioh ioh.zip MIT ioh.pdf sUper_IL sUper_IL.zip MIT sUper_IL.pdf kgu_ryu kgu_ryu.zip MIT kgu_ryu.pdf takoyaki takoyaki.zip MIT takoyaki.pdf Hachi2 Hachi2.zip MIT Hachi2.pdf KP22 KP22.zip MIT KP22.pdf ice ice.zip MIT ice.pdf Ncu702 Ncu702.zip MIT … Continue reading 4th International AIWolf Competition Protocol Division — Source Code and Document
Thank you for participating in the Fourth International AIWolf Competition. In this year, we had two divisions: Protocol Division and Natural Language Division. Final Results of the Protocol Division In the Protocol Division, 49 agents participated in the initial round, and 15 finalists were selected for the final round. The finalists played 503,600 werewolf games, … Continue reading Final Results of the 4th International AIWolf Competition at CoG 2022
Please see this page.