Google Research

Federated Control with Hierarchical Multi-Agent Deep Reinforcement Learning

  • Saurabh Kumar
  • Pararth Shah
  • Dilek Hakkani-Tur
  • Larry Heck
arXiv preprint arXiv:1712.08266 (2017)


We present a framework combining hierarchical and multi-agent deep reinforcement learning approaches to solve coordination problems among a multitude of agents using a semi-decentralized model. The framework extends the multi-agent learning setup by introducing a meta-controller that guides the communication between agent pairs, enabling agents to focus on communicating with only one other agent at any step. This hierarchical decomposition of the task allows for efficient exploration to learn policies that identify globally optimal solutions even as number of collaborating agents increases. We show initial experimental results on a simulated multi-task dialogue problem.

Research Areas

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work