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

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.

arXiv commentICML 2021 camera ready

References in corpus (9)

• Playing Atari with Deep Reinforcement Learning
• High-Dimensional Continuous Control Using Generalized Advantage Estimation
• Dota 2 with Large Scale Deep Reinforcement Learning
• StarCraft II: A New Challenge for Reinforcement Learning
• Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games
• Relational Deep Reinforcement Learning
• Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks
• TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game
• TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game

Cited by in corpus (4)

• Distributed Deep Reinforcement Learning: A Survey and A Multi-Player Multi-Agent Learning Toolbox
• AI in Human-computer Gaming: Techniques, Challenges and Opportunities
• SC2EGSet: StarCraft II Esport Replay and Game-state Dataset
• Applying supervised and reinforcement learning methods to create neural-network-based agents for playing StarCraft II