Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games

Understand

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.