Deep Reinforcement Learning for Dynamic Spectrum Access in the Multi-Channel Wireless Local Area Networks

White spaces pattern finding and inference based on machine learning for multi-frequency spectrum footprints

“…Therefore, the computational complexity of machine learning increase exponentially with the degrees of freedom. For improving the algorithms computational performance further advancements have been done combining supervised learning for Deep Neural Networks and Reinforcement Learning like Deep Q-Learning [28] and also on mixed algorithms like Genetic Algorithms with supervised machine learning [29]. Although, a higher accuracy and adaptability to different environment and scenarios is achieved, it still comes at a significant computational cost that might not be effective for some use cases considering the current state of the art regarding Edge Tensor Processing Unit [30,31,32].…”