Learning to reflect: a unifying approach for data-driven stochastic control strategies
DOI10.3150/23-BEJ1665MaRDI QIDQ6565314FDOQ6565314
Authors: Sören Christensen, Claudia Strauch, Lukas Trottner 
Publication date: 2 July 2024
Published in: Bernoulli (Search for Journal in Brave)
nonparametric statisticsdiffusion processesreinforcement learningovershootssup-norm riskLévy processesexploration vs. exploitationdata-driven singular control
Processes with independent increments; Lévy processes (60G51) Density estimation (62G07) Markov processes: estimation; hidden Markov models (62M05)
Cites Work
- Probability and random processes.
- High-dimensional probability. An introduction with applications in data science
- Applied Probability and Queues
- Mixing Conditions for Markov Chains
- Functional estimation for Lévy measures of semimartingales with Poissonian jumps
- Controlled diffusion models for optimal dividend pay-out
- Density Estimation of Lévy Measures for Discretely Observed Diffusion Processes with Jumps
- Statistical inference for ergodic diffusion processes.
- Fluctuations of Lévy processes with applications. Introductory lectures
- Meromorphic Lévy processes and their fluctuation identities
- Title not available (Why is that?)
- Title not available (Why is that?)
- Asymptotic statistical equivalence for scalar ergodic diffusions
- An introduction to stochastic differential equations with reflection
- Optimal harvesting of stochastically fluctuating populations
- Fluctuations of stable processes and exponential functionals of hypergeometric Lévy processes
- Exact and asymptotic \(n\)-tuple laws at first and last passage
- OPTIMAL DIVIDEND POLICY WITH MEAN-REVERTING CASH RESERVOIR
- A class of solvable stochastic dividend optimization problems: on the general impact of flexibility on valuation
- Asymptotic harvesting of populations in random environments
- Concentration of scalar ergodic diffusions and some statistical implications
- Applied stochastic control of jump diffusions
- A Note on a Change of Variable Formula with Local Time-Space for Lévy Processes of Bounded Variation
- Adaptive invariant density estimation for continuous-time mixing Markov processes under sup-norm risk
- A solution technique for Lévy driven long term average impulse control problems
- Stability of overshoots of Markov additive processes
Cited In (1)
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)
