Year: 2017
Type: preprint
Abstract: 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 the number of collaborating agents increases. We show promising initial experimental results on a simulated distributed scheduling problem.
Source: arXiv (Cornell University)
Institutions: Google (United States), Georgia Institute of Technology
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2781238083