Multi-Player Bandits - a Musical Chairs Approach

@inproceedings{Rosenski2016MultiPlayerB,
  title={Multi-Player Bandits - a Musical Chairs Approach},
  author={Jonathan Rosenski and Ohad Shamir and Liran Szlak},
  booktitle={ICML},
  year={2016}
}
We consider a variant of the stochastic multi-armed bandit problem, where multiple players simultaneously choose from the same set of arms and may collide, receiving no reward. This setting has been motivated by problems arising in cognitive radio networks, and is especially challenging under the realistic assumption that communication between players is limited. We provide a communication-free algorithm (Musical Chairs) which attains constant regret with high probability, as well as a… CONTINUE READING
Highly Cited
This paper has 24 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 16 times. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 16 extracted citations

Multi-Player Bandit Model with Different

View 11 Excerpts
Highly Influenced

{Multi-Player Bandits Revisited}

View 10 Excerpts
Highly Influenced

Distributed algorithm for dynamic spectrum access in infrastructure-less cognitive radio network

2018 IEEE Wireless Communications and Networking Conference (WCNC) • 2018
View 8 Excerpts
Highly Influenced

Distributed learning algorithms for coordination in a cognitive network in presence of jammers

2018 16th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt) • 2018
View 4 Excerpts
Highly Influenced

Trekking based distributed algorithm for opportunistic spectrum access in infrastructure-less network

2018 16th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt) • 2018
View 10 Excerpts
Highly Influenced

Multi-Player Bandits Models Revisited

B ESSON, E MILIE
2017
View 5 Excerpts
Highly Influenced

References

Publications referenced by this paper.
Showing 1-9 of 9 references

Distributed Algorithms for Learning and Cognitive Medium Access with Logarithmic Regret

IEEE Journal on Selected Areas in Communications • 2011
View 4 Excerpts
Highly Influenced

Regret analysis of stochastic and nonstochastic multiarmed bandit problems

Sébastien Bubeck, Nicolò Cesa-Bianchi
arXiv preprint 1204.5721, • 2012
View 1 Excerpt

Time Synchronization of Cognitive Radio Networks

GLOBECOM 2009 - 2009 IEEE Global Telecommunications Conference • 2009

Similar Papers

Loading similar papers…