Modeling Unit Classes as Agents in Real-Time Strategy Games


  • Ulit Jaidee Lehigh University
  • Hector Munoz-Avila Lehigh University



Computer Games, agents, learning


We present CLASSQL, 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 CLASSQL against the built-in AI in a variety of maps using the Wargus real-time strategy game.




How to Cite

Jaidee, U., & Munoz-Avila, H. (2021). Modeling Unit Classes as Agents in Real-Time Strategy Games. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 9(1), 149-155.