On solutions of the distributional Bellman equation

DOI10.3934/era.2023228arXiv2202.00081OpenAlexW4380996818MaRDI QIDQ6153120

Julian Gerstenberg, Ralph Neininger, Denis Spiegel

Publication date: 13 February 2024

Published in: Electronic Research Archive (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2202.00081

zbMATH Keywords

regular variationMarkov decision processmachine learningrandom difference equationperpetuitydistributional reinforcement learningdistributional Bellman equation

Mathematics Subject Classification ID

Computational learning theory (68Q32) Stationary stochastic processes (60G10) Numerical analysis or methods applied to Markov chains (65C40) Random operators and equations (aspects of stochastic analysis) (60H25) Numerical solutions to stochastic differential and integral equations (65C30) Numerical methods for difference equations (65Q10)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• A fixed point theorem for distributions
• Strict stationarity of generalized autoregressive processes
• Stability of perpetuities
• Conditions for convergence of random coefficient \(\mathrm{AR}(1)\) processes and perpetuities in higher dimensions
• Stochastic Models with Power-Law Tails
• On a stochastic difference equation and a representation of non–negative infinitely divisible random variables
• The stochastic equation Y_n+1=A_nY_n + B_n with stationary coefficients
• Discounted MDP’s: Distribution Functions and Exponential Utility Maximization
• Stability of perpetuities in Markovian environment
• Foundations of Modern Probability
• Distributional Reinforcement Learning

This page was built for publication: On solutions of the distributional Bellman equation