Automated Play-Testing Through RL Based Human-Like Play-Styles Generation - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Automated Play-Testing Through RL Based Human-Like Play-Styles Generation


The increasing complexity of gameplay mechanisms in modern video games is leading to the emergence of a wider range of ways to play games. The variety of possible play-styles needs to be anticipated by designers, through automated tests. Reinforcement Learning is a promising answer to the need of automating video game testing. To that effect one needs to train an agent to play the game, while ensuring this agent will generate the same play-styles as the players in order to give meaningful feedback to the designers. We present CARMI: a Configurable Agent with Relative Metrics as Input. An agent able to emulate the players play-styles, even on previously unseen levels. Unlike current methods it does not rely on having full trajectories, but only summary data. Moreover it only requires little human data, thus compatible with the constraints of modern video game production. This novel agent could be used to investigate behaviors and balancing during the production of a video game with a realistic amount of training time.
Fichier principal
Vignette du fichier
AIIDE_22_CARMI_format (40).pdf (1.62 Mo) Télécharger le fichier

Dates and versions

hal-03957672 , version 1 (20-03-2023)



Pierre Le Pelletier de Woillemont, Rémi Labory, Vincent Corruble. Automated Play-Testing Through RL Based Human-Like Play-Styles Generation. AIIDE'22: Artificial Intelligence and Interactive Digital Entertainment, AAAI, Oct 2022, Ponoma, CA, United States. pp.146-154, ⟨10.1609/aiide.v18i1.21958⟩. ⟨hal-03957672⟩
62 View
48 Download



Gmail Facebook X LinkedIn More