Shuhong Dai
  • about
  • blog
  • publications
  • Why SUMO’s Rendered Videos Should Never Be Used as RL Training Data

    A examination of why the visual output of SUMO. Despite being clean and intuitive, it cannot serve as learning data for RL agents, and why this limitation is inherent in how the simulator is built.

    5 min read   ·   January 27, 2025

    2025   ·   Simulation   Traffic   RL   SUMO

  • Re-running an RL Experiment and Getting a Different Answer

    A engineering reflection on why two RTX 4090 machines produced diverging RL curves despite identical code, seeds, and configurations. And what this reveals about RL’s numerical sensitivity.

    5 min read   ·   November 17, 2024

    2024   ·   Reinforcement Learning   CUDA   Numerical Stability   Reproducibility

  • Using Local v2rayN Proxy for Cloud Servers via SSH Reverse Tunnel

    A practical record of troubleshooting outbound network restrictions on Chinese cloud servers and enabling stable access to foreign academic resources.

    5 min read   ·   February 02, 2024

    2024   ·   Networking   Proxy   SSH   DevOps

  • Newer
  • 1
  • 2
  • Older
© Copyright 2025 Shuhong Dai.