Decoding of Polar Codes Based on Q-Learning-Driven Belief Propagation

TL;DR

This paper introduces a novel reinforcement learning-based belief propagation decoding algorithm for polar codes that improves decoding performance by adaptively reweighting message inputs, outperforming traditional methods.

Contribution

It proposes a Q-learning-driven belief propagation decoding method for polar codes, combining heuristic reweighting with reinforcement learning to enhance decoding accuracy.

Findings

Outperforms traditional BP and SC decoders in simulations.

Approaches the performance of SCL decoders.

Demonstrates improved decoding success rates.

Abstract

This paper presents an enhanced belief propagation (BP) decoding algorithm and a reinforcement learning-based BP decoding algorithm for polar codes. The enhanced BP algorithm weighs each Processing Element (PE) input based on their signals and Euclidean distances using a heuristic metric. The proposed reinforcement learning-based BP decoding strategy relies on reweighting the messages and consists of two steps: we first weight each PE input based on their signals and Euclidean distances using a heuristic metric, then a Q-learning algorithm (QLBP) is employed to figure out the best correction factor for successful decoding. Simulations show that the proposed enhanced BP and QLBP decoders outperform the successive cancellation (SC) and belief propagation (BP) decoders, and approach the SCL decoders.