Arbitrary side observations in bandit problems
From MaRDI portal
Publication:2483920
DOI10.1016/j.aam.2004.10.004zbMath1152.91391MaRDI QIDQ2483920
Sanjeev R. Kulkarni, Chih-Chun Wang, H. Vincent Poor
Publication date: 1 August 2005
Published in: Advances in Applied Mathematics (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/j.aam.2004.10.004
Efficient; Adaptive; Asymptotic; Regret; Arbitrary; Allocation rule; Evenly distributed; Side information; Two-armed bandit
60G40: Stopping times; optimal stopping problems; gambling theory
91A60: Probabilistic games; gambling
Related Items
Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback, A linear response bandit problem, Modeling item-item similarities for personalized recommendations on Yahoo! front page, Woodroofe's one-armed bandit problem revisited
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Asymptotically efficient adaptive allocation rules
- One-armed bandit problems with covariates
- Asymptotically efficient adaptive allocation schemes for controlled Markov chains: finite parameter space
- Covariate models for bernoulli bandits
- Asymptotically efficient allocation rules for the multiarmed bandit problem with multiple plays-Part I: I.I.D. rewards
- Asymptotically efficient allocation rules for the multiarmed bandit problem with multiple plays-Part II: Markovian rewards
- Asymptotically efficient adaptive allocation schemes for controlled i.i.d. processes: finite parameter space
- Asymptotically efficient adaptive allocation rules for the multiarmed bandit problem with switching cost
- A One-Armed Bandit Problem with a Concomitant Variable
- Finite-time lower bounds for the two-armed bandit problem
- Optimal allocations in sequential tests involving two populations with covariates
- Machine learning and nonparametric bandit theory
- Bandit problems with side observations
- A Bernoulli Two-armed Bandit
- Some aspects of the sequential design of experiments
- Learning while searching for the best alternative