Display Publications by [Year] [Type] [Topic]
Difference rewards (a particular instance of reward shaping) have been used to allow multiagent domains to scale to large numbers of agents, but they remain difficult to compute in many domains. We present an approach to modeling the global reward using function approximation that allows the quick computation of shaped difference rewards. We demonstrate how this model can result in significant improvements in behavior for two air traffic control problems. We show how the model of the global reward may be either learned on- or off-line using a linear combination of neural networks.
@inproceedings{tumer-proper_aamas12,
author = {S. Proper and K. Tumer},
title = {Modeling Difference Rewards for Multiagent Learning (Extended Abstract)},
booktitle = {Proceedings of the Eleventh International Joint Conference on Autonomous Agents and Multiagent Systems},
month = {June},
address = {Valencia, Spain},
abstract={Difference rewards (a particular instance of reward shaping) have been used to allow multiagent domains to scale to large numbers of agents, but they remain difficult to compute in many domains. We present an approach to modeling the global reward using function approximation that allows the quick computation of shaped difference rewards. We demonstrate how this model can result in significant improvements in behavior for two air traffic control problems. We show how the model of the global reward may be either learned on- or off-line using a linear combination of neural networks.},
bib2html_pubtype = {Refereed Conference Papers},
bib2html_rescat = {Multiagent Systems},
year = {2012}
}
Generated by bib2html.pl (written by Patrick Riley ) on Wed Apr 01, 2020 17:39:43