DeepAI AI Chat
Log In Sign Up

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

by   Peng Peng, et al.

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.


page 3

page 6

page 7

page 8

page 9

page 10

page 11


Pow-Wow: A Dataset and Study on Collaborative Communication in Pommerman

In multi-agent learning, agents must coordinate with each other in order...

Coordination in Adversarial Sequential Team Games via Multi-Agent Deep Reinforcement Learning

Many real-world applications involve teams of agents that have to coordi...

Any-Play: An Intrinsic Augmentation for Zero-Shot Coordination

Cooperative artificial intelligence with human or superhuman proficiency...

Opponent-aware Role-based Learning in Team Competitive Markov Games

Team competition in multi-agent Markov games is an increasingly importan...

A Communication Protocol for Man-Machine Networks

One of the most challenging coordination problems in artificial intellig...

Seq2Seq Mimic Games: A Signaling Perspective

We study the emergence of communication in multiagent adversarial settin...

Elo Ratings for Large Tournaments of Software Agents in Asymmetric Games

The Elo rating system has been used world wide for individual sports and...