Regret of Multi-Channel Bandit Game in Cognitive Radio Networks
The problem of how to evaluate the rate of convergence to Nash equilibrium solutions in the process of channel selection under incomplete information is studied. In this paper, the definition of regret is used to reflect the convergence rates of online algorithms. The process of selecting an idle ch...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
EDP Sciences
2016-01-01
|
Series: | MATEC Web of Conferences |
Subjects: | |
Online Access: | http://dx.doi.org/10.1051/matecconf/20165605002 |
id |
doaj-61d45cdbc32047df9143b509846f5505 |
---|---|
record_format |
Article |
spelling |
doaj-61d45cdbc32047df9143b509846f55052021-02-02T00:57:37ZengEDP SciencesMATEC Web of Conferences2261-236X2016-01-01560500210.1051/matecconf/20165605002matecconf_iccae2016_05002Regret of Multi-Channel Bandit Game in Cognitive Radio NetworksMa JunZhang YonghongThe problem of how to evaluate the rate of convergence to Nash equilibrium solutions in the process of channel selection under incomplete information is studied. In this paper, the definition of regret is used to reflect the convergence rates of online algorithms. The process of selecting an idle channel for each secondary user is modeled as a multi-channel bandit game. The definition of the maximal averaged regret is given. Two existing online learning algorithms are used to obtain the Nash equilibrium for each SU. The maximal averaged regrets are used to evaluate the performances of online algorithms. When there is a pure strategy Nash equilibrium in the multi-channel bandit game, the maximal averaged regrets are finite. A cooperation mechanism is also needed in the process of calculating the maximal averaged regrets. Simulation results show the maximal averaged regrets are finite and the online algorithm with greater convergence rate has less maximal averaged regrets.http://dx.doi.org/10.1051/matecconf/20165605002cognitive radio networksadversarial bandit problemcongestion gameonline learningdynamic spectrum access |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ma Jun Zhang Yonghong |
spellingShingle |
Ma Jun Zhang Yonghong Regret of Multi-Channel Bandit Game in Cognitive Radio Networks MATEC Web of Conferences cognitive radio networks adversarial bandit problem congestion game online learning dynamic spectrum access |
author_facet |
Ma Jun Zhang Yonghong |
author_sort |
Ma Jun |
title |
Regret of Multi-Channel Bandit Game in Cognitive Radio Networks |
title_short |
Regret of Multi-Channel Bandit Game in Cognitive Radio Networks |
title_full |
Regret of Multi-Channel Bandit Game in Cognitive Radio Networks |
title_fullStr |
Regret of Multi-Channel Bandit Game in Cognitive Radio Networks |
title_full_unstemmed |
Regret of Multi-Channel Bandit Game in Cognitive Radio Networks |
title_sort |
regret of multi-channel bandit game in cognitive radio networks |
publisher |
EDP Sciences |
series |
MATEC Web of Conferences |
issn |
2261-236X |
publishDate |
2016-01-01 |
description |
The problem of how to evaluate the rate of convergence to Nash equilibrium solutions in the process of channel selection under incomplete information is studied. In this paper, the definition of regret is used to reflect the convergence rates of online algorithms. The process of selecting an idle channel for each secondary user is modeled as a multi-channel bandit game. The definition of the maximal averaged regret is given. Two existing online learning algorithms are used to obtain the Nash equilibrium for each SU. The maximal averaged regrets are used to evaluate the performances of online algorithms. When there is a pure strategy Nash equilibrium in the multi-channel bandit game, the maximal averaged regrets are finite. A cooperation mechanism is also needed in the process of calculating the maximal averaged regrets. Simulation results show the maximal averaged regrets are finite and the online algorithm with greater convergence rate has less maximal averaged regrets. |
topic |
cognitive radio networks adversarial bandit problem congestion game online learning dynamic spectrum access |
url |
http://dx.doi.org/10.1051/matecconf/20165605002 |
work_keys_str_mv |
AT majun regretofmultichannelbanditgameincognitiveradionetworks AT zhangyonghong regretofmultichannelbanditgameincognitiveradionetworks |
_version_ |
1724312609893646336 |