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

Tags

Readers

  • Distributed Systems and Data Platform Development
  • Neural Network Machine Learning.
  • Research Science/Academic Research

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - DoD AI Strategy