Skip to Main content Skip to Navigation
New interface
Conference papers

Combinatorial Bandits Revisited

Abstract : This paper investigates stochastic and adversarial combinatorial multi-armed bandit problems. In the stochastic setting under semi-bandit feedback, we derive a problem-specific regret lower bound, and discuss its scaling with the dimension of the decision space. We propose ESCB, an algorithm that efficiently exploits the structure of the problem and provide a finite-time analysis of its regret. ESCB has better performance guarantees than existing algorithms, and significantly outperforms these algorithms in practice. In the adversarial setting under bandit feedback, we propose CombEXP, an algorithm with the same regret scaling as state-of-the-art algorithms, but with lower computational complexity for some combinatorial problems.
Complete list of metadata

Cited literature [27 references]  Display  Hide  Download
Contributor : Richard Combes Connect in order to contact the contributor
Submitted on : Thursday, April 9, 2020 - 6:34:04 PM
Last modification on : Saturday, June 25, 2022 - 10:45:02 PM


Files produced by the author(s)


  • HAL Id : hal-01257796, version 1
  • ARXIV : 1502.03475


Richard Combes, Sadegh Talebi, Alexandre Proutière, Marc Lelarge. Combinatorial Bandits Revisited. NIPS 2015 - Twenty-ninth Conference on Neural Information Processing Systems, Dec 2015, Montreal, Canada. ⟨hal-01257796⟩



Record views


Files downloads