A unified approach to Markov decision problems and performance sensitivity analysis with discounted and average criteria: multichain cases
- 31 October 2004
- journal article
- research article
- Published by Elsevier in Automatica
- Vol. 40 (10) , 1749-1759
Abstract
No abstract availableKeywords
This publication has 17 references indexed in Scilit:
- CONVERGENCE OF SIMULATION-BASED POLICY ITERATIONProbability in the Engineering and Informational Sciences, 2003
- From Perturbation Analysis to Markov Decision Processes and Reinforcement LearningDiscrete Event Dynamic Systems, 2003
- Infinite-Horizon Policy-Gradient EstimationJournal of Artificial Intelligence Research, 2001
- A unified approach to Markov decision problems and performance sensitivity analysisAutomatica, 2000
- The Maclaurin series for performance functions of Markov chainsAdvances in Applied Probability, 1998
- Algorithms for sensitivity analysis of Markov systems through potentials and perturbation realizationIEEE Transactions on Control Systems Technology, 1998
- The Relations Among Potentials, Perturbation Analysis, and Markov Decision ProcessesDiscrete Event Dynamic Systems, 1998
- Perturbation realization, potentials, and sensitivity analysis of Markov processesIEEE Transactions on Automatic Control, 1997
- A Fixed Point Approach to Undiscounted Markov Renewal ProgramsSIAM Journal on Algebraic Discrete Methods, 1984
- Discrete Dynamic ProgrammingThe Annals of Mathematical Statistics, 1962