Multi-Agent Reinforcement Learning for Cooperative and Competitive Undersea Environments
Abstract
Multi-Agent Reinforcement Learning for Cooperative and Competitive Undersea EnvironmentsThe Navy is interested in rapidly fielding artificial intelligence (AI) and machine learning (ML) algorithms. This proposal seeks funding to develop research supporting the design, analysis, and demonstration of the efficacy of a hybrid offline/online machine learning approach to rapidly mature technology for fielding. Specifically, this family of approaches will be applied to coordinatedplanning problems for maritime vehicles. The technical approach is structured along three interconnected thrusts that touch upon cooperative and non-cooperative simultaneous action games and deployment and task planning under uncertainty. The proposed research is a collaboration betweenthe Naval Information Warfare Center Pacific (NIWC Pacific) and the University of California, San Diego. The proposal seeks funding for one PhD student for three years, and for the PIs and the student to attend annual ONR program reviews.This project abstract is approved for public release.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Aug 31, 2020
- Source ID
- N000142012730
Entities
People
- Jorge Cortés
Organizations
- Office of Naval Research
- United States Navy
- University of California, San Diego