Playing the Werewolf game with artificial intelligence for language understanding

• URL: http://arxiv.org/abs/2302.10646v1
• Date: Tue, 21 Feb 2023 13:03:20 GMT
• Title: Playing the Werewolf game with artificial intelligence for language understanding
• Abstract summary: Werewolf is a social deduction game based on free natural language communication. The purpose of this study is to develop an AI agent that can play Werewolf through natural language conversations.
• Score: 0.7550566004119156
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The Werewolf game is a social deduction game based on free natural language communication, in which players try to deceive others in order to survive. An important feature of this game is that a large portion of the conversations are false information, and the behavior of artificial intelligence (AI) in such a situation has not been widely investigated. The purpose of this study is to develop an AI agent that can play Werewolf through natural language conversations. First, we collected game logs from 15 human players. Next, we fine-tuned a Transformer-based pretrained language model to construct a value network that can predict a posterior probability of winning a game at any given phase of the game and given a candidate for the next action. We then developed an AI agent that can interact with humans and choose the best voting target on the basis of its probability from the value network. Lastly, we evaluated the performance of the agent by having it actually play the game with human players. We found that our AI agent, Deep Wolf, could play Werewolf as competitively as average human players in a villager or a betrayer role, whereas Deep Wolf was inferior to human players in a werewolf or a seer role. These results suggest that current language models have the capability to suspect what others are saying, tell a lie, or detect lies in conversations.

Related papers

• CaM-Wolf: Causal-Aware Multimodal Agents for Social Deduction Games [41.77561512638328]
  Social deduction games (SDGs) such as Werewolf have become challenging testbeds for AI agents.<n>CaM-Wolf processes video inputs from other players, employs a causal-aware Reasoner trained via reinforcement learning to establish logical chains between observable behaviors and hidden roles.<n>Our experiments and user study show that CaM-Wolf achieves superior agent gameplay performance and enhances the quality of human-AI interaction.
  arXiv  Detail & Related papers  (2026-07-29T01:58:36Z)
• Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information [2.3101858435998346]
  Werewolf Game is a communication game where players' reasoning and discussion skills are essential.<n>We present a Werewolf AI agent developed for the AIWolfDial 2024 shared task, co-hosted with the 17th INLG.
  arXiv  Detail & Related papers  (2026-03-07T08:41:46Z)
• AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games [63.29377274531968]
  We introduce the AI GameStore, a scalable and open-ended platform to synthesize new representative human games.<n>We generate 100 such games based on the top charts of Apple App Store and Steam, and evaluate seven frontier vision-language models (VLMs) on short episodes of play.<n>The best models achieved less than 10% of the human average score on the majority of the games, and especially struggled with games that challenge world-model learning, memory and planning.
  arXiv  Detail & Related papers  (2026-02-19T18:17:25Z)
• An Implementation of Werewolf Agent That does not Truly Trust LLMs [0.8811927506272431]
  Werewolf is an incomplete information game, which has several challenges when creating a computer agent as a player. We propose a werewolf agent that solves some of those difficulties by combining a Large Language Model (LLM) and a rule-based algorithm.
  arXiv  Detail & Related papers  (2024-09-03T03:16:03Z)
• Explaining How a Neural Network Play the Go Game and Let People Learn [26.192580802652742]
  The AI model has surpassed human players in the game of Go. It is widely believed that the AI model has encoded new knowledge about the Go game beyond human players.
  arXiv  Detail & Related papers  (2023-10-15T13:57:50Z)
• Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Models [0.0]
  We introduce a text-based game called $textitHoodwinked$, inspired by Mafia and Among Us. Players are locked in a house and must find a key to escape, but one player is tasked with killing the others. We conduct experiments with agents controlled by GPT-3, GPT-3.5, and GPT-4 and find evidence of deception and lie detection capabilities.
  arXiv  Detail & Related papers  (2023-07-05T17:22:09Z)
• The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling Probabilistic Social Inferences from Linguistic Inputs [50.32802502923367]
  We study the process of language driving and influencing social reasoning in a probabilistic goal inference domain. We propose a neuro-symbolic model that carries out goal inference from linguistic inputs of agent scenarios. Our model closely matches human response patterns and better predicts human judgements than using an LLM alone.
  arXiv  Detail & Related papers  (2023-06-25T19:38:01Z)
• Human or Not? A Gamified Approach to the Turing Test [11.454575816255039]
  We present "Human or Not?", an online game inspired by the Turing test. The game was played by over 1.5 million users over a month. Overall users guessed the identity of their partners correctly in only 68% of the games. In the subset of the games in which users faced an AI bot, users had even lower correct guess rates of 60%.
  arXiv  Detail & Related papers  (2023-05-31T16:32:22Z)
• Promptable Game Models: Text-Guided Game Simulation via Masked Diffusion Models [68.85478477006178]
  We present a Promptable Game Model (PGM) for neural video game simulators. It allows a user to play the game by prompting it with high- and low-level action sequences. Most captivatingly, our PGM unlocks the director's mode, where the game is played by specifying goals for the agents in the form of a prompt. Our method significantly outperforms existing neural video game simulators in terms of rendering quality and unlocks applications beyond the capabilities of the current state of the art.
  arXiv  Detail & Related papers  (2023-03-23T17:43:17Z)
• Computational Charisma -- A Brick by Brick Blueprint for Building Charismatic Artificial Intelligence [98.79723276712419]
  Charisma is considered as one's ability to attract and potentially also influence others. There can be considerable interest from an AI's perspective to provide it with such skill. We present a blueprint for building machines that can appear charismatic, but also analyse the charisma of others.
  arXiv  Detail & Related papers  (2022-12-31T07:27:01Z)
• Are AlphaZero-like Agents Robust to Adversarial Perturbations? [73.13944217915089]
  AlphaZero (AZ) has demonstrated that neural-network-based Go AIs can surpass human performance by a large margin. We ask whether adversarial states exist for Go AIs that may lead them to play surprisingly wrong actions. We develop the first adversarial attack on Go AIs that can efficiently search for adversarial states by strategically reducing the search space.
  arXiv  Detail & Related papers  (2022-11-07T18:43:25Z)
• A Novel Weighted Ensemble Learning Based Agent for the Werewolf Game [0.0]
  Werewolf is a popular party game throughout the world, and research on its significance has progressed in recent years. In this research, we generated a sophisticated agent to play the Werewolf game using a complex weighted ensemble learning approach.
  arXiv  Detail & Related papers  (2022-05-19T19:19:29Z)
• Teach me to play, gamer! Imitative learning in computer games via linguistic description of complex phenomena and decision tree [55.41644538483948]
  We present a new machine learning model by imitation based on the linguistic description of complex phenomena. The method can be a good alternative to design and implement the behaviour of intelligent agents in video game development.
  arXiv  Detail & Related papers  (2021-01-06T21:14:10Z)
• Suphx: Mastering Mahjong with Deep Reinforcement Learning [114.68233321904623]
  We design an AI for Mahjong, named Suphx, based on deep reinforcement learning with some newly introduced techniques. Suphx has demonstrated stronger performance than most top human players in terms of stable rank. This is the first time that a computer program outperforms most top human players in Mahjong.
  arXiv  Detail & Related papers  (2020-03-30T16:18:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.