Enhancing Player Enjoyment with a Two-Tier DRL and LLM-Based Agent System for Fighting Games
This addresses the problem of enhancing player enjoyment for fighting game developers and players, though it is incremental as it builds on existing DRL and LLM methods.
The authors tackled the lack of player enjoyment-focused agents in fighting games by proposing a two-tier DRL and LLM-based system for Street Fighter II, resulting in up to 156.36% improvement in advanced skill execution and validated enjoyment in user feedback.
Deep reinforcement learning (DRL) has effectively enhanced gameplay experiences and game design across various game genres. However, few studies on fighting game agents have focused explicitly on enhancing player enjoyment, a critical factor for both developers and players. To address this gap and establish a practical baseline for designing enjoyability-focused agents, we propose a two-tier agent (TTA) system and conducted experiments in the classic fighting game Street Fighter II. The first tier of TTA employs a task-oriented network architecture, modularized reward functions, and hybrid training to produce diverse and skilled DRL agents. In the second tier of TTA, a Large Language Model Hyper-Agent, leveraging players' playing data and feedback, dynamically selects suitable DRL opponents. In addition, we investigate and model several key factors that affect the enjoyability of the opponent. The experiments demonstrate improvements from 64. 36% to 156. 36% in the execution of advanced skills over baseline methods. The trained agents also exhibit distinct game-playing styles. Additionally, we conducted a small-scale user study, and the overall enjoyment in the player's feedback validates the effectiveness of our TTA system.