Nonparametric learning for impulse control problems -- exploration vs. exploitation
DOI10.1214/22-aap1849arXiv1909.09528OpenAlexW4353080926MaRDI QIDQ6104004
No author found.
Publication date: 5 June 2023
Published in: The Annals of Applied Probability (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1909.09528
diffusion processesreinforcement learningnonparametric statisticsstochastic impulse controloptimal harvesting problemexploration vs. exploitationFaustmann problem
Markov processes: estimation; hidden Markov models (62M05) Learning and adaptive systems in artificial intelligence (68T05) Optimal stochastic control (93E20) Diffusion processes (60J60)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- On data-based optimal stopping under stationarity and ergodicity
- Statistical inference for ergodic diffusion processes.
- Nonparametric estimation of scalar diffusions based on low frequency data
- A class of solvable impulse control problems
- Concentration of scalar ergodic diffusions and some statistical implications
- Optimal decision under ambiguity for diffusion processes
- Continuous inventory models of diffusion type: long-term average cost criterion
- Brownian Motion, Martingales, and Stochastic Calculus
- Minimizing the Probability of Lifetime Ruin Under Ambiguity Aversion
- Adaptive Robust Control under Model Uncertainty
- Optimal Stopping With Multiple Priors
- On L2 Efficiency of an Empiric Distribution for Ergodic Diffusion Processes
- Anscombe’s model for sequential clinical trials revisited
- Stochastic Forest Stand Value and Optimal Timber Harvesting
- Bandit Algorithms
- Competition versus Cooperation: A Class of Solvable Mean Field Impulse Control Problems
- A weak convergence approach to inventory control using a long-term average criterion
- Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
- Improved Rates for the Stochastic Continuum-Armed Bandit Problem
- Portfolio optimization with unobservable Markov-modulated drift process
This page was built for publication: Nonparametric learning for impulse control problems -- exploration vs. exploitation