Variance-penalized Markov decision processes: dynamic programming and reinforcement learning techniques

ISSN： 0308-1079

Source： International Journal of General Systems, Vol.43, Iss.6, 2014-08, pp. : 649-669

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Related content

Reinforcement Learning Based Algorithms for Average Cost Markov Decision Processes

By Abdulla Mohammed Bhatnagar Shalabh

Discrete Event Dynamic Systems, Vol. 17, Iss. 1, 2007-03 ,pp. : 23-52

Springer Publishing Company

Access to resources Recommend Favorite

Discounted continuous-time Markov decision processes with unbounded rates and randomized history-dependent policies: the dynamic programming approach

By Piunovskiy Alexey Zhang Yi

4OR: Quarterly journal of the Belgian, French and Italian operations research societies, Vol. 12, Iss. 1, 2014-03 ,pp. : 49-75

Springer Publishing Company

Access to resources Recommend Favorite

Dynamic Workflow Composition: Using Markov Decision Processes

International Journal of Web Services Research (IJWSR), Vol. 2, Iss. 1, 2005-01 ,pp. : 1-17

IGI Global_journal

Access to resources Recommend Favorite

Constrained Markov decision processes with first passage criteria

By Huang Yonghui

Annals of Operations Research, Vol. 206, Iss. 1, 2013-07 ,pp. : 197-219

Springer Publishing Company

Access to resources Recommend Favorite

APPLICATION OF MARKOV DECISION PROCESSES TO THE FREQUENCY ASSIGNMENT PROBLEM

By GREFF JEAN-YVES

Applied Artificial Intelligence, Vol. 18, Iss. 8, 2004-09 ,pp. : 761-773

Taylor & Francis Ltd

Access to resources Recommend Favorite