Learning to reflect: a unifying approach for data-driven stochastic control strategies
From MaRDI portal
Publication:6565314
DOI10.3150/23-BEJ1665MaRDI QIDQ6565314
Claudia Strauch, Lukas Trottner, Sören Christensen
Publication date: 2 July 2024
Published in: Bernoulli (Search for Journal in Brave)
Lévy processesdiffusion processesreinforcement learningnonparametric statisticsovershootssup-norm riskexploration vs. exploitationdata-driven singular control
Processes with independent increments; Lévy processes (60G51) Density estimation (62G07) Markov processes: estimation; hidden Markov models (62M05)
Cites Work
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Meromorphic Lévy processes and their fluctuation identities
- Asymptotic statistical equivalence for scalar ergodic diffusions
- Exact and asymptotic \(n\)-tuple laws at first and last passage
- Functional estimation for Lévy measures of semimartingales with Poissonian jumps
- Optimal harvesting of stochastically fluctuating populations
- Controlled diffusion models for optimal dividend pay-out
- Statistical inference for ergodic diffusion processes.
- Asymptotic harvesting of populations in random environments
- Fluctuations of stable processes and exponential functionals of hypergeometric Lévy processes
- Concentration of scalar ergodic diffusions and some statistical implications
- 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
- Fluctuations of Lévy processes with applications. Introductory lectures
- A class of solvable stochastic dividend optimization problems: on the general impact of flexibility on valuation
- Probability and random processes.
- Density Estimation of Lévy Measures for Discretely Observed Diffusion Processes with Jumps
- OPTIMAL DIVIDEND POLICY WITH MEAN-REVERTING CASH RESERVOIR
- Mixing Conditions for Markov Chains
- High-Dimensional Probability
- Applied Probability and Queues
- A Note on a Change of Variable Formula with Local Time-Space for Lévy Processes of Bounded Variation
- Applied stochastic control of jump diffusions
- Stability of overshoots of Markov additive processes
Related Items (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)