Solution Procedures for Partially Observed Markov Decision Processes
From MaRDI portal
Publication:4735053
DOI10.1287/opre.37.5.791zbMath0684.90099OpenAlexW2167596735MaRDI QIDQ4735053
Chelsea C. III White, William T. Scherer
Publication date: 1989
Published in: Operations Research (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1287/opre.37.5.791
infinite horizonsuccessive approximationsmodified policy iterationexpected discounted total reward partially observed Markov decision process
Numerical mathematical programming methods (65K05) Markov and semi-Markov decision processes (90C40)
Related Items
A two-state partially observable Markov decision process with three actions, On the construction of \(\epsilon\)-optimal strategies in partially observed MDPs, A survey of algorithmic methods for partially observed Markov decision processes, A nonlinear programming model for partially observable Markov decision processes: Finite horizon case, State observation accuracy and finite-memory policy performance, Planning and acting in partially observable stochastic domains, On replacement policies for additive systems with several working levels, A tutorial on partially observable Markov decision processes, A survey of solution techniques for the partially observed Markov decision process, Optimal cost and policy for a Markovian replacement problem, A leader-follower partially observed, multiobjective Markov game, Value of information for a leader-follower partially observed Markov game
