SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II

TL;DR

The paper introduces SCC, a deep reinforcement learning agent for StarCraft II that achieves top human performance with significantly less computation than previous methods, demonstrating robustness and novel strategies.

Contribution

SCC is a new RL agent that outperforms prior models in StarCraft II using much less computational resources and incorporates key insights for efficient learning.

Findings

SCC defeats GrandMaster and professional players in test matches and live events.

SCC exhibits robustness to various human strategies.

SCC discovers novel strategies unseen in human gameplay.

Abstract

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.