Performance potential-based neuro-dynamic programming for SMDPs

Zidonghua Xuebao/Acta Automatica Sinica

Volumn 31, Issue 4, 2005, Pages 642-645

  Tang, Hao ^a   Yuan, Ji Bin ^a   Lu, Yang ^a   Cheng, Wen Juan ^a  

^a HEFEI UNIVERSITY OF TECHNOLOGY   (China)

Author keywords

Neuro dynamic programming; Performance potentials; Semi Markov decision processes

Indexed keywords

ALGORITHMS; COMPUTER SIMULATION; DECISION MAKING; DYNAMIC PROGRAMMING; ERROR CORRECTION; ITERATIVE METHODS; MATHEMATICAL MODELS; OPTIMIZATION;

ALPHA UNIFORMIZED MARKOV CHAIN; AVERAGE CRITERIA; DISCOUNTED CRITERIA; ERROR BOUNDS; INFINITESIMAL GENERATORS; NEURO DYNAMIC PROGRAMMING; PERFORMANCE POTENTIALS; SEMI MARKOV DECISION PROCESSES;

MARKOV PROCESSES;

EID: 23444449149     PISSN: 02544156     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (13)

1. Cao X R, Chen H F. Perturbation realization, potentials and sensitivity analysis of Markov processes. IEEE Transactions on Automatic Control, 1997, 42(10): 1382-1393
2. Cao X R. The relations among potentials, perturbation analysis, and Markov decision processes. Discrete Event Dynamic Systems: Theory and Applications, 1998, 8(1): 71-78
3. Cao X R. Single sample path-based optimization of Markov chains. Journal of Optimization Theory and Applications, 1999, 100(3): 527-548
4. Tang H, Xi H S, Yin B Q. Performance optimization of continuous-time Markov control processes based on performance potentials. International Journal of Systems Science, 2003, 34(1): 63-71
5. Tang H, Han J H, Gao J. Optimal robust control policy for continuous-time Markov control processes with average-cost criteria, Journal of University of Science and Technology of China, 2003, 34(2): 219-225
6. Bertsekas D P, Tsitsiklis J N. Neuro-dynamic Programming. Belmont, MA: Athena Scientific, 1996
7. Puterman M L. Markov Decision Processes: Discrete Stochastic Dynamic Programming. New York: Wiley, 1994
8. Tang H, Xi H S, Yin B Q. An on-line optimization algorithm for Markov control processes based on a single sample path. Control Theory and Applications, 2002, 19(6): 863-871
9. Tang H, Xi H S, Yin B Q. A simulation optimization algorithm for CTMDPs based on randomized stationary policies. Acta Automatica Sinica, 2004, 30(2): 229-234
10. Cao X R. Semi-Markov decision problems and performance sensitivity analysis. IEEE Transactions on Automatic Control, 2003, 48(5): 758-769
11. Yin B Q, Xi H S, Zhou Y P. Queueing System Performance Analysis and Markov Control Processes. Hefei: Press of University of Science and Technology of China, 2004
12. Liu Z K, Tu F S. Single sample path-based sensitivity analysis of Markov processes. IEEE Transactions on Automatic Control, 1999, 44(4): 872-875
13. Yuan J B, Tang H, Han J H. The NDP optimization of Markov decision processes based on TD(0) learning and performance potentials. In: Proceedings of The 23rd Chinese Control Conference, Wuxi: Press of Eastern China University of Technology, 2004