Concurrent Learning of Control in Multi-agent Sequential Decision Tasks

Document Type

Article

Publication Date

4-17-2018

School

Computing Sciences and Computer Engineering

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.

Find in your library

Share

COinS