Accession Number : AD1053581

Title :   Concurrent Learning of Control in Multi-agent Sequential Decision Tasks

Descriptive Note : Technical Report,01 May 2011,30 Apr 2015

Corporate Author : University of Southern Mississippi Hattiesburg United States

Personal Author(s) : Banerjee,Bikramjit

Full Text :

Report Date : 17 Apr 2018

Pagination or Media Count : 6

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.

Descriptors :   MULTIAGENT SYSTEMS , models , learning , artificial intelligence

Subject Categories : Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE