MULTI-ARMED BANDITS WITH COVARIATES:THEORY AND APPLICATIONS
From MaRDI portal
Publication:5072149
DOI10.5705/ss.202020.0454OpenAlexW3106747220MaRDI QIDQ5072149
Tze Leung Lai, Huanzhong Xu, Dongwoo Kim
Publication date: 25 April 2022
Published in: Statistica Sinica (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.5705/ss.202020.0454
reinforcement learningpersonalized medicinerecommender systemcontextual multi-armed bandits\(\epsilon\)-greedy randomization
Related Items
Bandit and covariate processes, with finite or non-denumerable set of arms, Encounters with Martingales in Statistics and Stochastic Optimization, Matrices -- compensating the loss of anschauung
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Information and asymptotic efficiency in parametric-nonparametric models
- Nonparametric bandit methods
- Woodroofe's one-armed bandit problem revisited
- Asymptotically efficient adaptive allocation rules
- Adaptive treatment allocation and the multi-armed bandit problem
- On adaptive estimation
- One-armed bandit problems with covariates
- Rates of convergence for minimum contrast estimators
- Convergence rate of sieve estimates
- Information-theoretic determination of minimax rates of convergence
- Multivariate locally weighted least squares regression
- Statistical science in information technology and precision medicine
- Minimax-optimal nonparametric regression in high dimensions
- Local linear regression smoothers and their minimax efficiencies
- Optimal stopping and dynamic allocation
- A One-Armed Bandit Problem with a Concomitant Variable
- Machine learning and nonparametric bandit theory
- Bandit problems with side observations
- Some aspects of the sequential design of experiments
- Finite-time analysis of the multiarmed bandit problem
