Digitalisation in education and its influence on teaching methods is the
focus of this study, which examines the use of ChatGPT in a role-playing game
used in the Cloud Computing Engineering Master's programme at the University of
Applied Sciences Burgenland. The aim of the study was to analyse the impact of
AI-based simulations on students' learning experience. Based on Vygotsky's
sociocultural theory, ChatGPT was used to give students a deeper understanding
of strategic decision-making processes in simulated business scenarios. The
methodological approach included role-playing and qualitative content analysis
of 20 student reflections. The findings suggest that ChatGPT enhances students'
engagement, critical thinking, and communication skills, in addition to
contributing to the effective application of theoretical knowledge.
Furthermore, simulations can contribute to the effective application of
theoretical knowledge. The results underscore the significance of adaptive
teaching approaches in promoting digital literacy and equipping learners for
the digital workplace. The integration of AI into curricula and the need for
ongoing innovation in higher education are also emphasised as a means of
guaranteeing excellent, future-focused instruction. The findings highlight the
potential of AI and ChatGPT in particular, as an innovative cutting-edge
educational tool that can both enhance the learning experience and help achieve
the Sustainable Development Goals (SDGs) through education.

数字化教育及其对教学方法的影响是这项研究的重点，该研究探讨了 ChatGPT 在应用科学布尔根兰应用科学大学云计算工程硕士课程中使用的角色扮演游戏中的应用。该研究的目的是分析人工智能模拟对学生学习体验的影响。研究采用维果茨基的社会文化理论，使用 ChatGPT 将学生带入模拟商业场景中的战略决策过程，以加深他们的理解。方法论包括角色扮演和对 20 个学生反思的定性内容分析。研究结果表明，ChatGPT 提高了学生的参与度、批判性思维和沟通技巧，同时有助于理论知识的有效应用。此外，模拟可以促进理论知识的有效应用。研究结果强调了自适应教学方法在促进数字素养和为数字职场装备学习者方面的重要性。将人工智能融入课程和高等教育领域持续创新的需求也被强调为确保优秀、面向未来的教学的手段。研究结果突出了人工智能特别是 ChatGPT 作为一种创新前沿教育工具的潜力，既能提升学习体验，又能通过教育实现可持续发展目标（SDGs）。

ChatGPT 改革角色扮演游戏

Revolutionising Role-Playing Games with ChatGPT

In a Role-Playing Game, finding optimal trajectories is one of the most
important tasks. In fact, the strategy decision system becomes a key component
of a game engine. Determining the way in which decisions are taken (online,
batch or simulated) and the consumed resources in decision making (e.g.
execution time, memory) will influence, in mayor degree, the game performance.
When classical search algorithms such as A* can be used, they are the very
first option. Nevertheless, such methods rely on precise and complete models of
the search space, and there are many interesting scenarios where their
application is not possible. Then, model free methods for sequential decision
making under uncertainty are the best choice. In this paper, we propose a
heuristic planning strategy to incorporate the ability of heuristic-search in
path-finding into a Dyna agent. The proposed Dyna-H algorithm, as A* does,
selects branches more likely to produce outcomes than other branches. Besides,
it has the advantages of being a model-free online reinforcement learning
algorithm. The proposal was evaluated against the one-step Q-Learning and
Dyna-Q algorithms obtaining excellent experimental results: Dyna-H
significantly overcomes both methods in all experiments. We suggest also, a
functional analogy between the proposed sampling from worst trajectories
heuristic and the role of dreams (e.g. nightmares) in human behavior.

本论文提出了一种基于启发式规划策略的路径规划方法，该方法在模型自由的在线强化学习中比传统的单步 Q 学习和 Dyna-Q 算法都表现出色，可以用于角色扮演游戏中的最优轨迹规划。