Aristotelis Lazaridis, Christos Perchanidis, Doxakis Chovardas and Ioannis Vlahavas. “AlphaBluff: An AI-Powered Heads-Up No-Limit Texas Hold’em Poker Video Game”. 16th International Conference on Innovations in Intelligent Systems and Applications (INISTA), Biarritz, France, 8-10 August, 2022.
Author(s): Lazaridis Aristotelis, Perchanidis Christos, Chovardas Doxakis, Vlahavas Ioannis
Keywords: artificial intelligence, reinforcement learning, games, poker
Tags:
Abstract: Complex games require disparate behaviors in order to be solved, giving space to researchers to study AI model behaviors in various settings. At the same time, the video game industry benefits by incorporating these models in their games for delivering realistic and challenging gameplay experience to users. However, there is a well-known difficulty of implementing and training efficient models in complex games for entertainment purposes. In this paper, we report on our approach to overcome this challenge and ultimately develop AlphaBluff, a Heads-Up No-Limit Texas Hold'em (HUNL) Poker variation video game developed in the Unity game engine, in which human players can play against trained AI opponents. Initially we trained different state-of-the-art AI models and analyzed their individual performance scores in a custom HUNL environment, as well as their performance against each other. AlphaBluff was developed with the goal of producing a professional-level poker video game that includes cutting-edge AI opponents, which, to our knowledge has never been developed before. Using data gathered by gameplay sessions from beta testers, we performed a statistical analysis and concluded that our models have a high win rate against human players. An adaptation of our system can further enrich this unique gameplay experience by combining these models, data and statistical reports, in order to develop an efficient player-opponent matchmaking mechanism.