Skip to content
Reinforcement Learning for Bit Flipping decoding of linear codes
Branch: master
Clone or download
Type Name Latest commit message Commit time
Failed to load latest commit information.
Hmat add paper and PC matrices Jun 12, 2019
LICENSE Initial commit Mar 19, 2019 expected code upload date Jun 12, 2019


RLdecoding is a collection of Python and Tensorflow scripts to learn Bit Flipping decoding through Reinforcement Learning.

Additional details are contained in this paper:

Parity Check matrices

The Parity Check (PC) matrices for the following codes are contained in the Hmat folder:

  • Reed–Muller (RM) codes:

    • RM(2,5)
    • RM(3,6)
    • RM(3,7)
    • RM(4,7)
  • Bose–Chaudhuri–Hocquenghem (BCH) codes:

    • BCH(63,45)

The suffix denotes:

  • _std: standard PC matrix
  • _oc: overcomplete PC matrix (the rows are dual codewords)

Getting Started

We are currently preparing the code for public release. We expect that it will be uploaded on or before July 15, 2019.

You can’t perform that action at this time.