Combinatorial Bandits Revisited

@inproceedings{Combes2015CombinatorialBR,
  title={Combinatorial Bandits Revisited},
  author={Richard Combes and Mohammad Sadegh Talebi and Alexandre Prouti{\`e}re and Marc Lelarge},
  booktitle={NIPS},
  year={2015}
}
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… CONTINUE READING
Highly Cited
This paper has 41 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 14 times over the past 90 days. VIEW TWEETS

From This Paper

Figures, tables, results, connections, and topics extracted from this paper.
29 Extracted Citations
29 Extracted References
Similar Papers

Citing Papers

Publications influenced by this paper.

Similar Papers

Loading similar papers…