AlphaStar, the AI that reaches GrandMaster level in StarCraft II, is a remarkable milestone demonstrating what deep reinforcement learning can achieve in complex Real-Time Strategy (RTS) games. However, the complexities of the game, algorithms and systems, and especially the tremendous amount of computation needed are big obstacles for the community to conduct further research in this direction. We propose a deep reinforcement learning agent, StarCraft Commander (SCC). With order of magnitude less computation, it demonstrates top human performance defeating GrandMaster players in test matches and top professional players in a live event. Moreover, it shows strong robustness to various human strategies and discovers novel strategies unseen from human plays. In this paper, we will share the key insights and optimizations on efficient imitation learning and reinforcement learning for StarCraft II full game.
@article{arxiv.2012.13169,
title = {SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II},
author = {Xiangjun Wang and Junxiao Song and Penghui Qi and Peng Peng and Zhenkun Tang and Wei Zhang and Weimin Li and Xiongjun Pi and Jujie He and Chao Gao and Haitao Long and Quan Yuan},
journal= {arXiv preprint arXiv:2012.13169},
year = {2021}
}