High-Level Representations for Game-Tree Search in RTS Games
Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment2014Vol. 10(2), pp. 14–18
Citations Over TimeTop 10% of 2014 papers
Abstract
From an AI point of view, Real-Time Strategy (RTS) games are hard because they have enormous state spaces, they are real-time and partially observable. In this paper, we explore an approach to deploy game-tree search in RTS games by using game state abstraction, and explore the effect of using different abstractions over the game state. Different abstractions capture different parts of the game state, and result in different branching factors when used for game-tree search algorithms. We evaluate the different representations using Monte Carlo Tree Search in the context of StarCraft.
Related Papers
- → Score Bounded Monte-Carlo Tree Search(2011)31 cited
- → Deep learning for general game playing with Ludii and Polygames(2022)12 cited
- → Computer games are an efficient tool for event game theory(2011)3 cited
- → RevCuT Tree Search Method in Complex Single-player Game with Continuous Search Space(2019)
- → Proof Number Based Monte-Carlo Tree Search(2023)