Piecewise linear approximations for partially observable Markov decision processes with finite horizons

Piecewise linear approximations for partially observable Markov decision processes with finite horizons

0.00 Avg rating0 Votes
Article ID: iaor19931177
Country: India
Volume: 13
Issue: 2
Start Page Number: 311
End Page Number: 324
Publication Date: May 1992
Journal: Journal of Information & Optimization Sciences
Authors:
Keywords: heuristics
Abstract:

This paper considers a finite horizon Markov decision process in which the state at any time is only known in terms of its probability vector at that time, which changes as additional information is required. The value function is known to be a piecewise linear function of the vector components. The paper considers procedures for finding an approximating set of linear forms, using linear programming and contraction and expansion heuristics.

Reviews

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 Your email address will not be published.