TY - GEN
T1 - Dynamic Channel Access via Meta-Reinforcement Learning
AU - Lu, Ziyang
AU - Gursoy, M. Cenk
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - In this paper, we address the channel access problem in a dynamic wireless environment via meta-reinforcement learning. Spectrum is a scarce resource in wireless communications, especially with the dramatic increase in the number of devices in networks. Recently, inspired by the success of deep reinforcement learning (DRL), extensive studies have been conducted in addressing wireless resource allocation problems via DRL. However, training DRL algorithms usually requires a massive amount of data collected from the environment for each specific task and the well-trained model may fail if there is a small variation in the environment. In this work, in order to address these challenges, we propose a meta-DRL framework that incorporates the method of Model-Agnostic Meta-Learning (MAML). In the proposed framework, we train a common initialization for similar channel selection tasks. From the initialization, we show that only a few gradient descents are required for adapting to different tasks drawn from the same distribution. We demonstrate the performance improvements via simulation results.
AB - In this paper, we address the channel access problem in a dynamic wireless environment via meta-reinforcement learning. Spectrum is a scarce resource in wireless communications, especially with the dramatic increase in the number of devices in networks. Recently, inspired by the success of deep reinforcement learning (DRL), extensive studies have been conducted in addressing wireless resource allocation problems via DRL. However, training DRL algorithms usually requires a massive amount of data collected from the environment for each specific task and the well-trained model may fail if there is a small variation in the environment. In this work, in order to address these challenges, we propose a meta-DRL framework that incorporates the method of Model-Agnostic Meta-Learning (MAML). In the proposed framework, we train a common initialization for similar channel selection tasks. From the initialization, we show that only a few gradient descents are required for adapting to different tasks drawn from the same distribution. We demonstrate the performance improvements via simulation results.
UR - http://www.scopus.com/inward/record.url?scp=85127274846&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85127274846&partnerID=8YFLogxK
U2 - 10.1109/GLOBECOM46510.2021.9685347
DO - 10.1109/GLOBECOM46510.2021.9685347
M3 - Conference contribution
AN - SCOPUS:85127274846
T3 - 2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings
BT - 2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE Global Communications Conference, GLOBECOM 2021
Y2 - 7 December 2021 through 11 December 2021
ER -