Multi-Agent Coordination in Open Environments

Abstract

This paper proposes a new approach to multi-agent systems leveraging from recent advances in networking and reinforcement learning to scale up teamwork based on joint intentions. In this approach, teamwork is subsumed by the coordination of learning agents. The intuition behind this approach is that successful coordination at the global level generates opportunities for teamwork interactions at the local level and vice versa. This unique approach scales up model-based teamwork theory with an adaptive approach to coordination. Some preliminary results are reported using a novel coordination evaluation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2006
Accession Number
ADA638191

Entities

People

  • Myriam Abramson
  • Ranjeev Mittu

Organizations

  • United States Naval Research Laboratory

Tags

Communities of Interest

  • Autonomy
  • Human Systems
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Collisions
  • Computing System Architectures
  • Environment
  • Information Exchange
  • Learning
  • Multiagent Systems
  • Networks
  • Probability
  • Psychological Phenomena And Processes
  • Psychology
  • Reinforcement Learning
  • Sensor Networks
  • Simulations
  • Teamwork
  • Test And Evaluation
  • Wireless Sensor Networks

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Computer Networking
  • Military Leadership and Professional Education.

Technology Areas

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