Average cost dynamic programming equations for controlled Markov chains with partial observations

Average cost dynamic programming equations for controlled Markov chains with partial observations

0.00 Avg rating0 Votes
Article ID: iaor2002430
Country: United States
Volume: 39
Issue: 3
Start Page Number: 673
End Page Number: 681
Publication Date: Oct 2000
Journal: SIAM Journal on Control and Optimization
Authors:
Keywords: markov processes
Abstract:

The value function for the average cost control of class of partially observed Markov chains is derived as the vanishing discount limit, in suitable sense, of the value functions for the corresponding discounted cost problems. The limiting procedure is justified by bounds derived using a simple coupling argument.

Reviews

Required fields are marked *. Your email address will not be published.