Mullet's Gambit: Explaining Learned Strategies in the Chef's Hat Multiplayer Card Game

• Published in: 2024 12th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW) pp. 136 - 143
• Main Authors: Triglia, Laura, Barros, Pablo, Rea, Francesco, Sciutti, Alessandra
• Format: Conference Proceeding
• Language: English
• Published: IEEE 15.09.2024
• Subjects: Computational modeling; Conferences; Decision making; Distance measurement; Explainable AI; Explainable game strategies; Gameplay analysis; Games; Heuristic algorithms; Humanagent interaction; Model Explainability; Navigation; Reinforcement learning; Strategic Interactions; Visualization

Reinforcement learning (RL)-based agents have demonstrated remarkable performance in multiplayer card game environments such as Chef's Hat. However, understanding why these agents excel in such dynamic and competitive settings remains a challenging endeavor. In this paper, we propose a novel me...