Asymmetric Action Abstractions for Multi-Unit Control in Adversarial Real-Time Games


  • Rubens Moraes Universidade Federal de Viçosa
  • Levi Lelis Universidade Federal de Viçosa


real-time strategy games, real-time adversarial planning, action abstractions


Action abstractions restrict the number of legal actions available during search in multi-unit real-time adversarial games, thus allowing algorithms to focus their search on a set of promising actions. Optimal strategies derived from un-abstracted spaces are guaranteed to be no worse than optimal strategies derived from action-abstracted spaces. In practice, however, due to real-time constraints and the state space size, one is only able to derive good strategies in un-abstracted spaces in small-scale games. In this paper we introduce search algorithms that use an action abstraction scheme we call asymmetric abstraction. Asymmetric abstractions retain the un-abstracted spaces' theoretical advantage over regularly abstracted spaces while still allowing the search algorithms to derive effective strategies, even in large-scale games. Empirical results on combat scenarios that arise in a real-time strategy game show that our search algorithms are able to substantially outperform state-of-the-art approaches.




How to Cite

Moraes, R., & Lelis, L. (2018). Asymmetric Action Abstractions for Multi-Unit Control in Adversarial Real-Time Games. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from



AAAI Technical Track: Game Playing and Interactive Entertainment