Multi-Agent Systems 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 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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 2004
Accession Number
ADA606300

Entities

People

  • Myriam Abramson
  • Ranjeev Mittu

Organizations

  • United States Naval Research Laboratory

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Abstracts
  • Autonomous Agents
  • Environment
  • Information Operations
  • Learning
  • Military Research
  • Multiagent Systems
  • New York
  • Reinforcement Learning
  • Teamwork
  • Workshops

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Distributed Systems and Data Platform Development
  • Joint Military Operations and Doctrine.

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy