A Deep Look into Trust and Mutual Understanding in Multi-Agent Cooperative Game Through Explainable Reinforcement Learning

Abstract

Establishing trust in autonomous systems trained by machine learning is one of the important steps towards fostering their acceptance. This requires those systems to provide explanations for their actions in a manner that is intuitive and understandable to humans. In a multi-agent cooperative environment where numerous agents collaborate to achieve a common mission, the trust existing among these agents, a concept inherently familiar to humans, significantly influences the success of the mission. Agent-to-agent (A2A) trust will become increasingly important as disparate companies, agencies, and other organizations deploy heterogenous autonomous systems that operate in a shared environment.

Document Details

Document Type
DoD Grant Award
Publication Date
Feb 05, 2025
Source ID
FA95502410078

Entities

People

  • Qinru Qiu

Organizations

  • Air Force Office of Scientific Research
  • Syracuse University
  • United States Air Force

Tags

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - DoD AI Strategy
  • Autonomy
  • Autonomy - Autonomous System Control
  • Autonomy - Human-Robot Interaction