Corpus ID: 211818094

Model Selection in Contextual Stochastic Bandit Problems

@article{Pacchiano2020ModelSI,
  title={Model Selection in Contextual Stochastic Bandit Problems},
  author={Aldo Pacchiano and My Phan and Yasin Abbasi-Yadkori and A. Rao and Julian Zimmert and Tor Lattimore and Csaba Szepesvari},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.01704}
}
We study model selection in stochastic bandit problems. Our approach relies on a master algorithm that selects its actions among candidate base algorithms. While this problem is studied for specific classes of stochastic base algorithms, our objective is to provide a method that can work with more general classes of stochastic base algorithms. We propose a master algorithm inspired by CORRAL \cite{DBLP:conf/colt/AgarwalLNS17} and introduce a novel and generic smoothing transformation for… Expand
15 Citations

Figures from this paper

Rate-adaptive model selection over a collection of black-box contextual bandit algorithms
  • 1
  • Highly Influenced
  • PDF
Regret Bound Balancing and Elimination for Model Selection in Bandits and RL
  • 3
  • PDF
Pareto Optimal Model Selection in Linear Bandits
  • Highly Influenced
  • PDF
Smooth Bandit Optimization: Generalization to Hölder Space
  • Highly Influenced
  • PDF
Adapting to Misspecification in Contextual Bandits
  • 4
  • PDF
Regret Balancing for Bandit and RL Model Selection
  • 5
  • PDF
Upper Confidence Bounds for Combining Stochastic Bandits
  • 1
  • Highly Influenced
  • PDF
Online Model Selection: a Rested Bandit Formulation
  • PDF
Multitask Bandit Learning through Heterogeneous Feedback Aggregation
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 35 REFERENCES
Model selection for contextual bandits
  • 24
  • Highly Influential
  • PDF
Corralling a Band of Bandit Algorithms
  • 54
  • PDF
Mostly Exploration-Free Algorithms for Contextual Bandits
  • 59
  • PDF
Provably Optimal Algorithms for Generalized Linear Contextual Bandits
  • 107
  • PDF
Nonparametric Stochastic Contextual Bandits
  • 12
  • PDF
Improved Algorithms for Linear Stochastic Bandits
  • 709
  • PDF
Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
  • 412
  • PDF
Learning with Good Feature Representations in Bandits and in RL with a Generative Model
  • 35
  • PDF
...
1
2
3
4
...