Reinforcement Learning for Bit-Flipping Decoding of Polar Codes

Abstract

A traditional successive cancellation (SC) decoding algorithm produces error propagation in the decoding process. In order to improve the SC decoding performance, it is important to solve the error propagation. In this paper, we propose a new algorithm combining reinforcement learning and SC flip (SCF) decoding of polar codes, which is called a Q-learning-assisted SCF (QLSCF) decoding algorithm. The proposed QLSCF decoding algorithm uses reinforcement learning technology to select candidate bits for the SC flipping decoding. We establish a reinforcement learning model for selecting candidate bits, and the agent selects candidate bits to decode the information sequence. In our scheme, the decoding delay caused by the metric ordering can be removed during the decoding process. Simulation results demonstrate that the decoding delay of the proposed algorithm is reduced compared with the SCF decoding algorithm, based on critical set without loss of performance.

Security Gap Improvement of BICM Systems Through Bit-Labeling Optimization for the Gaussian Wiretap Channel

“…Doan et al [383], [384] Neural DSCF with trainable bit-flipping metric. Wang et al [385] Q-learning-assisted SCF decoding algorithm. Doan et al [386] RL-based bit-flipping strategy for fast SC decoding.…”

“…In [383], [384], the authors proposed neural DSCF decoding where they properly approximated and introduced trainable parameters to the BF metric and optimized its parameter by RMSProp, a variant of the SGD optimization technique. In [385], the authors proposed a Q-learning-assisted SCF decoding algorithm that selects the candidate flipping bits through the learned Q-table instead of metric sorting. It was demonstrated that the proposed decoding algorithm is particularly effective in reducing the decoding delay caused by sorting during the decoding process without sacrificing performance.…”