Concurrent Learning of Control in Multi-agent Sequential Decision Tasks
Technical Report,01 May 2011,30 Apr 2015
University of Southern Mississippi Hattiesburg United States
Pagination or Media Count:
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.