Model-Based Reinforcement Learning for Wireless Channel Access

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, we study a wireless channel access method using model-based reinforcement learning in limited spectral resources. The proposed method maximizes sampling efficiency by learning an environment and using it for actor learning. The environment is a model that considers a dynamic packet queue in a situation where a wireless channel is shared. We show the performance results of the proposed learning algorithm in the considered environment.

Original languageEnglish
Title of host publicationICTC 2022 - 13th International Conference on Information and Communication Technology Convergence
Subtitle of host publicationAccelerating Digital Transformation with ICT Innovation
PublisherIEEE Computer Society
Pages1393-1395
Number of pages3
ISBN (Electronic)9781665499392
DOIs
StatePublished - 2022
Event13th International Conference on Information and Communication Technology Convergence, ICTC 2022 - Jeju Island, Korea, Republic of
Duration: 19 Oct 202221 Oct 2022

Publication series

NameInternational Conference on ICT Convergence
Volume2022-October
ISSN (Print)2162-1233
ISSN (Electronic)2162-1241

Conference

Conference13th International Conference on Information and Communication Technology Convergence, ICTC 2022
Country/TerritoryKorea, Republic of
CityJeju Island
Period19/10/2221/10/22

Keywords

  • actor-critic
  • model-based reinforcement learning
  • POMDP
  • wireless channel access
  • world model

Fingerprint

Dive into the research topics of 'Model-Based Reinforcement Learning for Wireless Channel Access'. Together they form a unique fingerprint.

Cite this