Optimizing CRC Polynomial Selection using Reinforcement Learning for Improved GRAND Decoding

This paper introduces a groundbreaking reinforcement learning (RL)-driven optimization framework for cyclic redundancy check (CRC) polynomials, tailored to meet the ultra-reliable low-latency communication (URLLC) and massive machine-type communication (mMTC) demands of 5G and beyond wireless networks. By addressing the critical challenge of undetectable error patterns (UEPs) in guessing random additive noise decoding (GRAND), our approach significantly enhances error detection and correction capabilities under stringent reliability constraints. Leveraging a markov decision process (MDP) model, we optimize CRC polynomial coefficients through Q-learning with -greedy exploration, where each action flips a coefficient and rewards are based on UEP reduction. This method ensures robust performance in additive white Gaussian noise (AWGN) channels, aligning with the ultra-reliability requirements of URLLC and the scalability needs of mMTC. Experimental results demonstrate substantial improvements in bit error rate (BER) and decoding reliability, paving the way for next-generation wireless standards. Our work bridges the gap between theoretical innovation and practical deployment, offering a scalable, learning-based solution for future high-performance communication systems.