mlsanityData to 14 Oct 2026

ZeroCode: On-demand Error-Correcting Code Construction from the Zero Matrix via Reinforcement Learning

arXiv 2609.34265 ↗First posted 28 Sep 2026cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

Error-correcting codes (ECCs) are essential across diverse applications, from wireless communications and storage to quantum computing, yet each application imposes distinct design requirements on the parity-check matrix (PCM). To address these on-demand requirements in a unified framework, we propose ZeroCode, a reinforcement learning (RL)-based approach that constructs PCMs sequentially from the all-zero matrix. ZeroCode formulates construction as a discrete sequential decision-making problem and uses proximal policy optimization with action masking to select valid edges. ZeroCode achieves a gain of approximately 1 dB over the prior RL-based construction method at a bit error rate (BER) of 10-4 for the (32,16) code and outperforms existing genetic, differentiable, and classical code-design methods in our experiments. Beyond optimizing decoding performance, the masking mechanism allows on-demand structural constraints, such as a maximum degree, 4-cycle-free structure, and quasi-cyclic structure, to be flexibly incorporated. Moreover, a single policy rollout yields a library of PCMs with varying edge counts, offering trade-offs between decoding performance and complexity without retraining. Overall, ZeroCode addresses diverse code-design requirements within a unified framework, providing solutions with optimized decoding performance under given constraints.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 14 of its 39 references that are in the map. First posted on arXiv 28 Sep 2026.

Builds on

14 of 39 references.

References · 14

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2015Continuous control with deep reinforcement learningcited by 3,407
  3. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  4. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,103
  5. 2020A Closer Look at Invalid Action Masking in Policy Gradient Algorithmscited by 171
  6. 2017Deep Learning Methods for Improved Decoding of Linear Codescited by 66
  7. 2022Error Correction Code Transformercited by 47
  8. 2018Large-scale Interactive Recommendation with Tree-structured Policy Gradientcited by 30
  9. 2024CrossMPT: Cross-attention Message-Passing Transformer for Error Correcting Codescited by 21
  10. 2023Boosting Learning for LDPC Codes to Improve the Error-Floor Performancecited by 10
  11. 2024Boosted Neural Decoders: Achieving Extreme Reliability of LDPC Codes for 6G Networkscited by 3
  12. 2024Factor Graph Optimization of Error-Correcting Codes for Belief Propagation Decodingcited by 3
2 more
  1. 2021RELDEC: Reinforcement Learning-Based Decoding of Moderate Length LDPC Codescited by 1
  2. 2024GNN-based Auto-Encoder for Short Linear Block Codes: A DRL Approachcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Discovering highly efficient low-weight quantum error-correcting codes with reinforcement learning
  2. 2026A Reinforcement Learning Based Universal Sequence Design for Polar Codes
  3. 2026Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination
  4. 2025Discovering autonomous quantum error correction via deep reinforcement learning
  5. 2026DiDPO: Diff-in-Diff Policy Optimization for Coding Agent Training
  6. 2026Reinforcement Learning for Code Optimization
  7. 2024A Reinforcement Learning Environment for Automatic Code Optimization in the MLIR Compiler
  8. 2026HLS-Seek: QoR-Aware Code Generation for High-Level Synthesis via Proxy Comparative Reward Reinforcement Learning