Predicting combat outcomes and optimizing armies in StarCraft II by deep learning

作者：

Highlights：

• Decision-making is a key-problem in real-time strategy games.

• Proposed method enhanced StarCraft II AI’s decision-making ability regardless of battlefields.

• A neural-network-based surrogate model resulted in rapid decision-making.

摘要

•Decision-making is a key-problem in real-time strategy games.•Proposed method enhanced StarCraft II AI’s decision-making ability regardless of battlefields.•A neural-network-based surrogate model resulted in rapid decision-making.

论文关键词：Deep learning,Deep neural network (DNN),Artificial intelligence (AI),Real-time strategy (RTS) games,StarCraft II,Combat win-rate prediction

论文评审过程：Received 12 October 2020, Revised 8 July 2021, Accepted 8 July 2021, Available online 24 July 2021, Version of Record 28 July 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115592