Home > Research > Publications & Outputs > CCN interest forwarding strategy as Multi-Armed...

Research

Associated organisational unit

Electronic data

Links

Keywords

View graph of relations

CCN interest forwarding strategy as Multi-Armed Bandit model with delays

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

CCN interest forwarding strategy as Multi-Armed Bandit model with delays. / Avrachenkov, Konstantin; Jacko, Peter.
Network Games, Control and Optimization (NetGCooP), 2012 6th International Conference on. New York: IEEE, 2012. p. 38-43.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Avrachenkov, K & Jacko, P 2012, CCN interest forwarding strategy as Multi-Armed Bandit model with delays. in Network Games, Control and Optimization (NetGCooP), 2012 6th International Conference on. IEEE, New York, pp. 38-43, 6th International Conference on Network Games, Control and OPtimization (NetGCooP), France, 28/11/12. <http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6486116>

APA

Avrachenkov, K., & Jacko, P. (2012). CCN interest forwarding strategy as Multi-Armed Bandit model with delays. In Network Games, Control and Optimization (NetGCooP), 2012 6th International Conference on (pp. 38-43). IEEE. http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6486116

Vancouver

Avrachenkov K, Jacko P. CCN interest forwarding strategy as Multi-Armed Bandit model with delays. In Network Games, Control and Optimization (NetGCooP), 2012 6th International Conference on. New York: IEEE. 2012. p. 38-43

Author

Avrachenkov, Konstantin ; Jacko, Peter. / CCN interest forwarding strategy as Multi-Armed Bandit model with delays. Network Games, Control and Optimization (NetGCooP), 2012 6th International Conference on. New York : IEEE, 2012. pp. 38-43

Bibtex

@inproceedings{8e45d1c601f043a092f2abb9c8834106,
title = "CCN interest forwarding strategy as Multi-Armed Bandit model with delays",
abstract = "We consider Content Centric Network (CCN) interest forwarding problem as a Multi-Armed Bandit (MAB) problem with delays. We investigate the transient behaviour of the epsilon-greedy, tuned epsilon-greedy and Upper Confidence Bound (UCB) interest forwarding policies. Surprisingly, for all the three policies very short initial exploratory phase is needed. We demonstrate that the tuned epsilon-greedy algorithm is nearly as good as the UCB algorithm, commonly reported as the best currently available algorithm. We prove the uniform logarithmic bound for the tuned epsilon-greedy algorithm in the presence of delays. In addition to its immediate application to CCN interest forwarding, the new theoretical results for MAB problem with delays represent significant theoretical advances in machine learning discipline.",
keywords = "PROBABILITY-INEQUALITIES, RANDOM-VARIABLES, RESPONSES",
author = "Konstantin Avrachenkov and Peter Jacko",
year = "2012",
language = "English",
isbn = "9781467360265",
pages = "38--43",
booktitle = "Network Games, Control and Optimization (NetGCooP), 2012 6th International Conference on",
publisher = "IEEE",
note = "6th International Conference on Network Games, Control and OPtimization (NetGCooP) ; Conference date: 28-11-2012 Through 30-11-2012",

}

RIS

TY - GEN

T1 - CCN interest forwarding strategy as Multi-Armed Bandit model with delays

AU - Avrachenkov, Konstantin

AU - Jacko, Peter

PY - 2012

Y1 - 2012

N2 - We consider Content Centric Network (CCN) interest forwarding problem as a Multi-Armed Bandit (MAB) problem with delays. We investigate the transient behaviour of the epsilon-greedy, tuned epsilon-greedy and Upper Confidence Bound (UCB) interest forwarding policies. Surprisingly, for all the three policies very short initial exploratory phase is needed. We demonstrate that the tuned epsilon-greedy algorithm is nearly as good as the UCB algorithm, commonly reported as the best currently available algorithm. We prove the uniform logarithmic bound for the tuned epsilon-greedy algorithm in the presence of delays. In addition to its immediate application to CCN interest forwarding, the new theoretical results for MAB problem with delays represent significant theoretical advances in machine learning discipline.

AB - We consider Content Centric Network (CCN) interest forwarding problem as a Multi-Armed Bandit (MAB) problem with delays. We investigate the transient behaviour of the epsilon-greedy, tuned epsilon-greedy and Upper Confidence Bound (UCB) interest forwarding policies. Surprisingly, for all the three policies very short initial exploratory phase is needed. We demonstrate that the tuned epsilon-greedy algorithm is nearly as good as the UCB algorithm, commonly reported as the best currently available algorithm. We prove the uniform logarithmic bound for the tuned epsilon-greedy algorithm in the presence of delays. In addition to its immediate application to CCN interest forwarding, the new theoretical results for MAB problem with delays represent significant theoretical advances in machine learning discipline.

KW - PROBABILITY-INEQUALITIES

KW - RANDOM-VARIABLES

KW - RESPONSES

M3 - Conference contribution/Paper

SN - 9781467360265

SP - 38

EP - 43

BT - Network Games, Control and Optimization (NetGCooP), 2012 6th International Conference on

PB - IEEE

CY - New York

T2 - 6th International Conference on Network Games, Control and OPtimization (NetGCooP)

Y2 - 28 November 2012 through 30 November 2012

ER -