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

TL;DR

This paper introduces asymmetric action abstractions for multi-unit control in real-time adversarial games, enabling effective strategy search in large-scale scenarios and outperforming existing methods.

Contribution

The paper proposes a novel asymmetric abstraction scheme that maintains theoretical guarantees while improving practical strategy derivation in large-scale real-time games.

Findings

Algorithms using asymmetric abstraction outperform state-of-the-art approaches.

Effective strategies are derived even in large-scale, real-time scenarios.

Empirical results demonstrate significant performance improvements.

Abstract

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.