Distributed Algorithms for Learning and Cognitive Medium Access with Logarithmic Regret

  title={Distributed Algorithms for Learning and Cognitive Medium Access with Logarithmic Regret},
  author={Anima Anandkumar and Nithin Michael and Ao Tang and Ananthram Swami},
  journal={IEEE Journal on Selected Areas in Communications},
The problem of distributed learning and channel access is considered in a cognitive network with multiple secondary users. The availability statistics of the channels are initially unknown to the secondary users and are estimated using sensing decisions. There is no explicit information exchange or prior agreement among the secondary users and sensing and access decisions are undertaken by them in a completely distributed manner. We propose policies for distributed learning and access which… CONTINUE READING
Highly Influential
This paper has highly influenced 27 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 197 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 134 extracted citations

Efficient decentralized dynamic spectrum learning and access policy for multi-standard multi-user cognitive radio networks

2014 11th International Symposium on Wireless Communications Systems (ISWCS) • 2014
View 15 Excerpts
Highly Influenced

Multi-Player Bandit Model with Different

View 8 Excerpts
Highly Influenced

{Multi-Player Bandits Revisited}

View 8 Excerpts
Highly Influenced

Multi-Player Bandits Models Revisited

View 8 Excerpts
Highly Influenced

QoS Driven Channel Selection Algorithm for Cognitive Radio Network: Multi-User Multi-Armed Bandit Approach

IEEE Transactions on Cognitive Communications and Networking • 2017
View 9 Excerpts
Highly Influenced

Traffic-Aware Online Network Selection in Heterogeneous Wireless Networks

IEEE Transactions on Vehicular Technology • 2016
View 6 Excerpts
Highly Influenced

Distributed opportunistic spectrum access with spatial reuse in cognitive radio networks

2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP) • 2014
View 4 Excerpts
Highly Influenced

198 Citations

Citations per Year
Semantic Scholar estimates that this publication has 198 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 25 references

Decentralized multi-armed bandit with multiple distributed players

2010 Information Theory and Applications Workshop (ITA) • 2010
View 19 Excerpts
Highly Influenced

Asymptotica lly Efficient Allocation Rules for the Multiarmed Bandit Problem with Mul tip e Plays-Part I: IID rewards

V. Anantharam, P. Varaiya, J. Walrand
IEEE Tran. on Auto. Control, vol. 32, no. 11, pp. 968–976, 1987. • 1987
View 4 Excerpts
Highly Influenced

Asymptotically Efficient Adaptive Allocation Rules

T L Lai Andherbertrobbins
View 6 Excerpts
Highly Influenced

Sample Mean Based Index Policies with O(logn) Regret for the Multi-Armed Bandit Problem

R. Agrawal
Advances in Applied Probability, vol. 27, no. 4, pp. 1054–1078, 1995. • 1995
View 5 Excerpts
Highly Influenced

Distributed learning under imperfect sensing in cognitive radio networks

2010 Conference Record of the Forty Fourth Asilomar Conference on Signals, Systems and Computers • 2010
View 1 Excerpt

Learning to Compete for Resources in Wireless Stochastic Games

IEEE Transactions on Vehicular Technology • 2009
View 1 Excerpt

Multi-agent Q-learning of channel selection in multi-user cognitive radio systems: A two by two case

2009 IEEE International Conference on Systems, Man and Cybernetics • 2009
View 1 Excerpt

Similar Papers

Loading similar papers…