Learning to reflect: a unifying approach for data-driven stochastic control strategies

DOI10.3150/23-BEJ1665MaRDI QIDQ6565314zbMATH OpenFDO

Authors Sören Christensen, Claudia Strauch, Lukas Trottner

Publication date 2 July 2024

Published in Bernoulli (Search for Journal in Brave)

Full work available at URL https://doi.org/10.3150/23-BEJ1665

zbMATH Keywords

data-driven singular controldiffusion processesexploration vs. exploitationLévy processesnonparametric statisticsovershootsreinforcement learningsup-norm risk

Mathematics Subject Classification ID

Processes with independent increments; Lévy processes (60G51) Density estimation (62G07) Markov processes: estimation; hidden Markov models (62M05)

Cites work

• A class of solvable stochastic dividend optimization problems: on the general impact of flexibility on valuation
• A Note on a Change of Variable Formula with Local Time-Space for Lévy Processes of Bounded Variation
• A solution technique for Lévy driven long term average impulse control problems
• Adaptive invariant density estimation for continuous-time mixing Markov processes under sup-norm risk
• An introduction to stochastic differential equations with reflection
• Applied Probability and Queues
• Applied stochastic control of jump diffusions
• Asymptotic harvesting of populations in random environments
• Asymptotic statistical equivalence for scalar ergodic diffusions
• Concentration of scalar ergodic diffusions and some statistical implications
• Controlled diffusion models for optimal dividend pay-out
• Density Estimation of Lévy Measures for Discretely Observed Diffusion Processes with Jumps
• Exact and asymptotic \(n\)-tuple laws at first and last passage
• Fluctuations of Lévy processes with applications. Introductory lectures
• Fluctuations of stable processes and exponential functionals of hypergeometric Lévy processes
• Functional estimation for Lévy measures of semimartingales with Poissonian jumps
• High-dimensional probability. An introduction with applications in data science
• scientific article; zbMATH DE number 1076783 (Why is no real title available?)
• scientific article; zbMATH DE number 3383329 (Why is no real title available?)
• Meromorphic Lévy processes and their fluctuation identities
• Mixing Conditions for Markov Chains
• OPTIMAL DIVIDEND POLICY WITH MEAN-REVERTING CASH RESERVOIR
• Optimal harvesting of stochastically fluctuating populations
• Probability and random processes.
• Stability of overshoots of Markov additive processes
• Statistical inference for ergodic diffusion processes.

Cited in

(2)

• Data-driven rules for multidimensional reflection problems
• Mini-workshop: Data-driven modeling, analysis, and control of dynamical systems. Abstracts from the mini-workshop held December 8--13, 2024

This page was built for publication: Learning to reflect: a unifying approach for data-driven stochastic control strategies

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6565314)