TY - JOUR AU - Jaidee, Ulit AU - Munoz-Avila, Hector PY - 2021/06/30 Y2 - 2024/03/29 TI - Modeling Unit Classes as Agents in Real-Time Strategy Games JF - Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment JA - AIIDE VL - 9 IS - 1 SE - Poster Papers DO - 10.1609/aiide.v9i1.12667 UR - https://ojs.aaai.org/index.php/AIIDE/article/view/12667 SP - 149-155 AB - <p> We present CLASS<sub>QL</sub>, a multi-agent model for playing real-time strategy games, where learning and control of our own team’s units is decentralized; each agent uses its own reinforcement learning process to learn and control units of the same class. Coordination between these agents occurs as a result of a common reward function shared by all agents and synergistic relations in a carefully crafted state and action model for each class. We present results of CLASS<sub>QL</sub> against the built-in AI in a variety of maps using the Wargus real-time strategy game. </p> ER -