About

I am a PhD student at Nanyang Technological University, working under the supervision of Dacheng Tao. Previously I completed my master's studies and began my research journey at Tsinghua University. Earlier, I obtained my bachelor's degree at Hunan University, where I cherished four wonderful years at the foothills of Yuelu Mountain.

My research goal is to unlock the true potential of Deep Reinforcement Learning toward practical real-world deployment. This requires RL agents capable of offline-online cooperation, handling multiple tasks, and never stopping learning in open-ended environments. To realize this vision, I currently focus on investigating the fundamental challenges inherent in DRL — particularly optimization pathologies, scalability limitations, and exploration inefficiencies.

Meanwhile, I view RL as a paradigm for understanding and developing intelligence rather than just a technique. This inspires my interest in exploring its potential across domains — from large reasoning models and embodied agents to psychology and social sciences.

guozheng001@e.ntu.edu.sg Google Scholar
An illustrated portrait of Guozheng Ma An illustrated portrait of Guozheng Ma

Education

  • Hunan University

    Bachelor's degree

  • Tsinghua University

    Master's degree · Research journey began

  • 2024–present

    Nanyang Technological University

    PhD student · Advised by Dacheng Tao

Service

  • Workshop organizer · RLC 2026 Continual Reinforcement Learning; NeurIPS 2025 Embodied World Models for Decision Making

  • Co-founder · Reinforcement Learning Evolution Foundation

  • Conference reviewer · ICML 2024–2025; NeurIPS 2024–2025; ICLR 2025; CVPR 2025; ICCV 2025; ECCV 2024; CoLLAs 2025

  • Journal reviewer · IEEE Transactions on Image Processing

  • Workshop PC · NeurIPS 2025 ARLET; ICLR 2025 MCDC; NeurIPS 2024 Continual FoMo and SoLaR; ICML 2024 TiFA, AutoRL and DMLR; NeurIPS 2023 SoLaR; ICML 2023 DMLR

Awards

  • Excellent Graduates · Beijing

  • ICLR Financial Assistance Award

  • ORDOS Scholarship · Tsinghua University

  • AI Safety and Alignment Fellowship · Concordia AI

  • Provincial Excellent Graduates · Hunan Province

  • First Prize of Outstanding Undergraduate Thesis · Hunan University

  • Weisheng Scholarship · Hunan University

  • XiongXiaoge Scholarship · Hunan University

  • National Scholarship · Ministry of Education of China

Talks

  • AI TIME · Youth PhD Talk · March

    Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages

    Watch the Talk
  • The 6th AI Academic Forum of Beijing Universities · April

    Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages

Updates