To cope with new communication applications and the rapid growth of network capacity, 6G wireless communication networks face serious challenges in terms of deep coverage, power consumption, cost, and ultra-dense connectivity. Reconfigurable intelligent surface (RIS) is a new and revolutionary technology that can effectively solve these problems. It intelligently reconfigures the propagation environment of wireless electromagnetic waves by integrating a large number of low-cost passive reflective elements on a single plane, which greatly increases the freedom of communication system design and can significantly improve the performance of wireless communication networks. In order to alleviate the coverage blindness of 6G networks, reduce system power consumption, and improve system throughput and spectral efficiency, RIS will certainly be widely used in future wireless communication networks. Nevertheless, the research on RIS-assisted communications is still in its initial stage, and there are several technical difficulties to be broken through, especially in resource allocation.

Resource allocation can improve system capacity and transmission rates by dynamically adjusting transmit power, subchannel allocation coefficients, available bandwidth, etc. However, traditional resource allocation techniques need to cost a massive number of iterations, regulate system parameters, and frequent information exchange, which is not very adaptable to wireless environments. To deal with these problems, artificial intelligence-based resource allocation techniques are necessary. Through the application of artificial intelligence (AI), machine learning (ML), and deep learning (DL), etc., dynamic resource allocation can be achieved without much channel training and a lot of iterative calculations. It can achieve network intelligence, radio resource intelligent management, and intelligent connectivity for everything.

This Special Issue aims to collate original research and review articles describing advances in this field.

Potential topics include but are not limited to the following:

• Novel theories, concepts, and architecture for AI resource allocation
• Challenges and solutions in AI-based resource allocation ultra-dense RIS scenarios
• AI-based beamforming design methods
• AI-based power allocation methods
• AI-based channel allocation methods
• AI-based user scheduling methods
• AI-based handoff methods
• AI-based computational methods
• AI-based RIS selection methods
• AI-based phase shift design methods
• AI-based mode selection methods
• Application of AI in wireless communications