Case-Based Goal-Driven Coordination of Multiple Learning Agents

Abstract

Although several recent studies have been published on goal reasoning (i.e., the study of agents that can self-select their goals), none have focused on the task of learning and acting on large state and action spaces. We introduce GDA-C, a case-based goal reasoning algorithm that divides the state and action space among cooperating learning agents. Cooperation between agents emerges because (1) they share a common reward function and (2) GDA-C formulates the goal that each agent needs to achieve. We claim that its case-based approach for goal formulation is critical to the agents performance. To test this claim we conducted an empirical study using the Wargus RTS environment, where we found that GDA-C outperforms its non-GDA ablation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2013
Accession Number
ADA602656

Entities

People

  • David W. Aha
  • Hector Munoz-avila
  • Ulit Jaidee

Organizations

  • United States Naval Research Laboratory

Tags

Communities of Interest

  • Autonomy
  • Counter WMD

DTIC Thesaurus Topics

  • Ablation
  • Algorithms
  • Artificial Intelligence
  • Autonomy
  • C Agents
  • Computer Science
  • Computers
  • Cooperation
  • Environment
  • Iterations
  • Learning
  • Military Research
  • Psychological Phenomena And Processes
  • Psychology
  • Reasoning
  • Reinforcement Learning
  • Training

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Artificial Intelligence

Technology Areas

  • Space
  • Space - Spacecraft Maneuvers