SeungGwan LEE


Policy Gradient Based Semi-Markov Decision Problems: Approximation and Estimation Errors
Ngo Anh VIEN SeungGwan LEE TaeChoong CHUNG 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2010/02/01
Vol. E93-D  No. 2  pp. 271-279
Type of Manuscript:  Special Section PAPER (Special Section on Foundations of Computer Science)
Category: 
Keyword: 
Markov decision processesdynamic programmingsemi-Markov decision processespolicy gradient SMDPapproximation and estimation error bounds
 Summary | Full Text:PDF(196.4KB)

Policy Gradient SMDP for Resource Allocation and Routing in Integrated Services Networks
Ngo Anh VIEN Nguyen Hoang VIET SeungGwan LEE TaeChoong CHUNG 
Publication:   IEICE TRANSACTIONS on Communications
Publication Date: 2009/06/01
Vol. E92-B  No. 6  pp. 2008-2022
Type of Manuscript:  PAPER
Category: Network
Keyword: 
call admission control (CAC)communication system controlcommunication system routingMarkov decision processesdynamic programmingsemi-Markov decision processes
 Summary | Full Text:PDF(401.9KB)