Strategy Game-Playing with Size-Constrained State Abstraction

TL;DR

This paper introduces size-constrained state abstraction (SCSA) for strategy game AI, which improves search efficiency and performance by limiting grouped nodes, eliminating the need to abandon abstractions mid-search, and demonstrating superior results across multiple games.

Contribution

The paper proposes a novel size-constrained state abstraction method that enhances game search algorithms without requiring abandonment of abstractions, improving robustness and performance.

Findings

SCSA outperforms previous abstraction methods in strategy games.

SCSA provides robust performance across different games.

Eliminates the need to abandon abstractions during search.

Abstract

Playing strategy games is a challenging problem for artificial intelligence (AI). One of the major challenges is the large search space due to a diverse set of game components. In recent works, state abstraction has been applied to search-based game AI and has brought significant performance improvements. State abstraction techniques rely on reducing the search space, e.g., by aggregating similar states. However, the application of these abstractions is hindered because the quality of an abstraction is difficult to evaluate. Previous works hence abandon the abstraction in the middle of the search to not bias the search to a local optimum. This mechanism introduces a hyper-parameter to decide the time to abandon the current state abstraction. In this work, we propose a size-constrained state abstraction (SCSA), an approach that limits the maximum number of nodes being grouped together. We found that with SCSA, the abstraction is not required to be abandoned. Our empirical results on $3$ strategy games show that the SCSA agent outperforms the previous methods and yields robust performance over different games. Codes are open-sourced at https://github.com/GAIGResearch/Stratega.