ICTACT Journal on Communication Technology

Dhananjay Kumar ¹, Pavithra Hari ¹, Panbhazhagi Selvaraj ¹, Sharavanti Baskaran ¹

Affiliations
1 Department of Information Technology, Anna University, MIT Campus, Chennai, IN

Abstract

Machine learning schemes can be employed in cognitive radio systems to intelligently locate the spectrum holes with some knowledge about the operating environment. In this paper, we formulate a variation of Actor Critic Learning algorithm known as Continuous Actor Critic Learning Automaton (CACLA) and compare this scheme with Actor Critic Learning scheme and existing Q-learning scheme. Simulation results show that our CACLA scheme has lesser execution time and achieves higher throughput compared to other two schemes.

Keywords

Markov Decision Process, Reinforcement Learning, Q–Learning, Actor–Critic Learning, CACLA.

Full Text