Deep Lifelong Reinforcement Learning for Resilient Control and Coordination

Abstract

The goal of this program is to incorporate lifelong transfer learning into deep reinforcement learning (DRL), yielding a system that can rapidly learn high performance policies for novel scenarios in multi-agent ISR environments.

Document Details

Document Type
DoD Grant Award
Publication Date
Oct 06, 2016
Source ID
FA87501610109

Entities

People

  • Eric Eaton

Organizations

  • Rome Laboratory
  • United States Air Force
  • University of Pennsylvania

Tags

Readers

  • Brain and Cognitive Science; Experimental Psychology; Cognitive Neuroscience
  • Distributed Systems and Data Platform Development
  • STEM Education

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - Neural Networks