Video Game
Video games serve as a rich testing ground for artificial intelligence research, focusing on areas like agent learning, decision-making, and human-computer interaction. Current research emphasizes the development and application of deep reinforcement learning (DRL), transformer networks, and evolutionary algorithms to improve agent performance, understand game dynamics, and enhance game design and testing. These advancements contribute to broader fields such as multi-agent systems, human-computer interaction, and even mechanism design, with practical applications ranging from personalized game experiences to automated game testing and improved AI safety evaluation.
Papers
SPRING: Studying the Paper and Reasoning to Play Games
Yue Wu, Shrimai Prabhumoye, So Yeon Min, Yonatan Bisk, Ruslan Salakhutdinov, Amos Azaria, Tom Mitchell, Yuanzhi Li
Regret Matching+: (In)Stability and Fast Convergence in Games
Gabriele Farina, Julien Grand-Clément, Christian Kroer, Chung-Wei Lee, Haipeng Luo