Reinforcement learning in learning automata and cellular learning automata via multiple reinforcement signals
作者：
Highlights：
• Reinforcement learning schemes are extended to learn using multiple feedbacks.
• Using separate feedbacks, the proposed models can learn an optimal subset of actions.
• The effectiveness of the proposed models is investigated experimentally.
• Theoretical convergence analysis of some of the presented models is provided.
摘要
•Reinforcement learning schemes are extended to learn using multiple feedbacks.•Using separate feedbacks, the proposed models can learn an optimal subset of actions.•The effectiveness of the proposed models is investigated experimentally.•Theoretical convergence analysis of some of the presented models is provided.
论文关键词：Learning automata,Cellular learning automata,Multi radio channel assignment
论文评审过程：Received 9 June 2018, Revised 13 January 2019, Accepted 15 January 2019, Available online 19 January 2019, Version of Record 18 February 2019.
论文官网地址：https://doi.org/10.1016/j.knosys.2019.01.021
