Reinforcement Learning Approaches and Evaluation Criteria for Opportunistic Spectrum Access

Clément Robert 1 Christophe Moy 1 Cheng-Xiang Wang 2
1 IETR - Institut d'Electronique et de Télécommunications de Rennes
2 HWU - Heriot-Watt University [Edinburgh]
Abstract : This paper deals with the learning and decision making issue for cognitive radio (CR). Two reinforcement-learning algorithms proposed in the literature are compared for opportunistic spectrum access (OSA): Upper Confidence Bound (UCB) algorithm and Weight Driven (WD) algorithm. This paper also introduces two new metrics in order to evaluate the machine learning algorithm performance for CR: effective cumulative regret and percentage of successful trials. They provide a fair evaluation means for CR performance.
Keywords : cognitive radio OSA reinforcement learning UCB weight-driven decision making convergence
Document type :
Conference papers
Complete list of metadatas
https://hal-supelec.archives-ouvertes.fr/hal-00994933
Contributor : Myriam Andrieux <>
Submitted on : Thursday, May 22, 2014 - 1:48:21 PM
Last modification on : Friday, November 16, 2018 - 1:25:57 AM

Identifiers

  • HAL Id : hal-00994933, version 1

Collections

UNIV-NANTES | UNIV-RENNES1 | SUPELEC | SUP_SCEE | SUP_IETR | IETR_SCEE | IETR | UR1-UFR-ISTIC | UNIV-RENNES | INSA-GROUPE

Citation

Clément Robert, Christophe Moy, Cheng-Xiang Wang. Reinforcement Learning Approaches and Evaluation Criteria for Opportunistic Spectrum Access. IEEE ICC'14, Jun 2014, Sydney, Australia. 6 p. ⟨hal-00994933⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

941

Contact

CCSD