An Unsupervised Video Game Playstyle Metric via State Discretization

Chiu Chou Lin, Wei Chen Chiu, I. Chen Wu

研究成果: Conference article同行評審


On playing video games, different players usually have their own playstyles. Recently, there have been great improvements for the video game AIs on the playing strength. However, past researches for analyzing the behaviors of players still used heuristic rules or the behavior features with the game-environment support, thus being exhausted for the developers to define the features of discriminating various playstyles. In this paper, we propose the first metric for video game playstyles directly from the game observations and actions, without any prior specification on the playstyle in the target game. Our proposed method is built upon a novel scheme of learning discrete representations that can map game observations into latent discrete states, such that playstyles can be exhibited from these discrete states. Namely, we measure the playstyle distance based on game observations aligned to the same states. We demonstrate high playstyle accuracy of our metric in experiments on some video game platforms, including TORCS, RGSK, and seven Atari games, and for different agents including rule-based AI bots, learning-based AI bots, and human players.

頁(從 - 到)215-224
期刊Proceedings of Machine Learning Research
出版狀態Published - 2021
事件37th Conference on Uncertainty in Artificial Intelligence, UAI 2021 - Virtual, Online
持續時間: 27 7月 202130 7月 2021


深入研究「An Unsupervised Video Game Playstyle Metric via State Discretization」主題。共同形成了獨特的指紋。