A Reinforcement Learning Based Universal Sequence Design for Polar Codes

TL;DR

This paper introduces a reinforcement learning framework for designing universal Polar code sequences that adapt to various channel conditions and decoding strategies, achieving competitive or improved performance for 6G applications.

Contribution

The work presents a scalable, adaptable RL-based sequence design method for Polar codes, incorporating physical constraints and multi-configuration optimization, suitable for standardization.

Findings

Achieves up to 0.2 dB gain over baseline at N=2048.

Scales to code lengths up to 2048, suitable for 6G.

Maintains competitive performance across all 5G-supported configurations.

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.