A Reinforcement Learning Based Universal Sequence Design for Polar Codes

2026-01-27

AI Summary

This work addresses the lack of a universal and scalable sequence design method for Polar codes in 6G under varying channel conditions and decoding strategies. To this end, the authors propose a reinforcement learning framework integrated with physical-layer constraints. For the first time, the partial order theory of Polar codes is embedded into the reinforcement learning architecture, combined with modeling of weak long-term dependencies and joint optimization across multiple configurations. This enables efficient and adaptive code construction for diverse blocklengths and rates (N, K). While maintaining full compatibility with 5G NR, the proposed approach matches the performance of all 5G-supported code profiles and achieves up to a 0.2 dB gain over the beta-expansion baseline at N = 2048, significantly enhancing generalization capability and training efficiency for large-scale code lengths.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Reinforcement Learning
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

To advance Polar code design for 6G applications, we develop a reinforcement learning-based universal sequence design framework that is extensible and adaptable to diverse channel conditions and decoding strategies. Crucially, our method scales to code lengths up to $2048$, making it suitable for use in standardization. Across all $(N,K)$ configurations supported in 5G, our approach achieves competitive performance relative to the NR sequence adopted in 5G and yields up to a 0.2 dB gain over the beta-expansion baseline at $N=2048$. We further highlight the key elements that enabled learning at scale: (i) incorporation of physical law constrained learning grounded in the universal partial order property of Polar codes, (ii) exploitation of the weak long term influence of decisions to limit lookahead evaluation, and (iii) joint multi-configuration optimization to increase learning efficiency.

Problem

• Polar codes
• sequence design
• 6G
• universal design
• channel conditions

Innovation

• Reinforcement Learning
• Polar Codes
• Universal Sequence Design
• Physical Law Constrained Learning
• Multi-Configuration Optimization