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

arXiv: https://arxiv.org/abs/1711.08101 · HTML: https://mlsanity.com/paper/1711.08101/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Nov 2017.

## Built on by (most cited first, 3 of 3)

- [Generating Diverse and Competitive Play-Styles for Strategy Games](https://mlsanity.com/paper/2104.08641/) (2021)
- [AUPO -- Abstracted Until Proven Otherwise: A Reward Distribution Based Abstraction Algorithm](https://mlsanity.com/paper/2510.23214/) (2025)
- [Hierarchical Reinforcement Learning in StarCraft Micromanagement with Influence Maps and Cluster-based Scripts](https://mlsanity.com/paper/2606.30092/) (2026)

## Abstract (arXiv)

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.