<ul><li>A Two-Tier DRL and LLM-Based Agent System for Fighting Games has been proposed to enhance player enjoyment.</li><li>The system consists of a task-oriented network architecture, hybrid training, and modularized reward functions for producing diverse and skilled DRL agents.</li><li>A Large Language Model Hyper-Agent is used to dynamically select suitable DRL opponents based on players' data and feedback.</li><li>Experiments show significant improvements in executing advanced skills and overall enjoyment, validating the effectiveness of the system.</li></ul>

Enhancing Player Enjoyment with a Two-Tier DRL and LLM-Based Agent System for Fighting Games

Discover more