Generative AI with GOAP for Fast-Paced Dynamic Decision-Making in Game Environments
Tiger Shan, Kay Michel · 2024
In this paper, we explore a novel approach to AI gaming. We combine Goal-Oriented Action Planning (GOAP) with the cognitive power of LLM such as ChatGPT. Our method tackles the issue of delayed responses commonly seen with Large Language Models (LLMs). This would be a research question that allows us to use the cognitive power of LLM in the fast-paced world of gaming. In this paper, we utilize GOAP to counter this problem, which allows agents to think strategically and make decisions on the fly, enhancing users’ overall gaming experience.