Concurrent Learning of Control in Multi-agent Sequential Decision Tasks

Abstract

The overall objective of this project was to develop multi-agent reinforcement learning (MARL) approaches for intelligent agents to autonomously learn distributed control policies in decentralized partially observable Markov decision processes (Dec-POMDPs), without prior knowledge of the model parameters.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 17, 2018
Accession Number
AD1053581

Entities

People

  • Bikramjit Banerjee

Organizations

  • University of Southern Mississippi

Tags

Communities of Interest

  • Autonomy
  • Human Systems

DTIC Thesaurus Topics

  • Abstracts
  • Adaptive Systems
  • Agreements
  • Algorithms
  • Artificial Intelligence
  • Autonomous Agents
  • Environment
  • Information Operations
  • Instructions
  • Intelligent Agents
  • Learning
  • Mathematics
  • Military Research
  • Mississippi
  • Multiagent Systems
  • Observation
  • Probability
  • Reinforcement Learning
  • Students
  • Surveillance
  • Theses
  • Uncertainty
  • Universities
  • Workshops

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Mathematical Modeling and Probability Theory.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms