Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games
This addresses the challenge of scalable multi-agent coordination for AI applications, with potential real-world impact, though it is incremental in applying a novel method to a known bottleneck.
The paper tackles the problem of enabling multiple AI agents to learn human-level coordination in StarCraft combat games without supervision, achieving state-of-the-art performance in experiments.
Many artificial intelligence (AI) applications often require multiple intelligent agents to work in a collaborative effort. Efficient learning for intra-agent communication and coordination is an indispensable step towards general AI. In this paper, we take StarCraft combat game as a case study, where the task is to coordinate multiple agents as a team to defeat their enemies. To maintain a scalable yet effective communication protocol, we introduce a Multiagent Bidirectionally-Coordinated Network (BiCNet ['bIknet]) with a vectorised extension of actor-critic formulation. We show that BiCNet can handle different types of combats with arbitrary numbers of AI agents for both sides. Our analysis demonstrates that without any supervisions such as human demonstrations or labelled data, BiCNet could learn various types of advanced coordination strategies that have been commonly used by experienced game players. In our experiments, we evaluate our approach against multiple baselines under different scenarios; it shows state-of-the-art performance, and possesses potential values for large-scale real-world applications.