On Finite Approximations to Markov Decision Processes with Recursive and Nonlinear Discounting

DOI10.1007/978-3-030-76928-4_11zbMath1478.90140OpenAlexW3172743656MaRDI QIDQ5153610

Xin Guo, Yi Zhang, Fan Deng

Publication date: 30 September 2021

Published in: Modern Trends in Controlled Stochastic Processes: (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-3-030-76928-4_11

zbMATH Keywords

Markov decision processeserror boundfinite approximationsnonlinear discounting

Mathematics Subject Classification ID

Approximation methods and heuristics in mathematical programming (90C59) Markov and semi-Markov decision processes (90C40)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On variable discounting in dynamic programming: applications to resource extraction and other economic models
• Approximation of Markov decision processes with general state space
• Berge's theorem for noncompact image sets
• Finite approximations in discrete-time stochastic control. Quantized models and asymptotic optimality
• Generalised discounting in dynamic programming with unbounded returns
• Stochastic dynamic programming with non-linear discounting
• Convergence of discretization procedures in dynamic programming
• Approximation of Infinite Horizon Discounted Cost Markov Decision Processes
• Applications of variable discounting dynamic programming to iterated function systems and related problems
• Average Optimality in Markov Control Processes via Discounted-Cost Problems and Linear Programming
• Continuous-Time Markov Decision Processes
• Persistently Optimal Policies in Stochastic Dynamic Programming with Generalized Discounting
• Approximations of Countably Infinite Linear Programs over Bounded Measure Spaces

This page was built for publication: On Finite Approximations to Markov Decision Processes with Recursive and Nonlinear Discounting