avatar

Guozheng Ma

PhD Student
Nanyang Technological University

GUOZHENG001 (at) e.ntu.edu.sg


Short Bio

Currently, I am a first-year PhD student at NTUNanyang Technological University, working under the supervision of Dacheng Tao. Previously, I embarked on my research path as a master student at THU Tsinghua University, studying Visual Reinforcement Learning and Data Augmentation. Prior to that, I completed my bachelor's degree at HNU Hunan University, where I cherished four wonderful years at the foothills of Yuelu Mountain.

My research interests broadly pertain to the distinctive challenges in DEEP Reinforcement Learning. Mitigating the constraints that arise when integrating deep neural networks with RL paradigms is crucial for unlocking the potential of RL, determining whether DEEP RL agents can tackle complex real-world scenarios, handle multiple tasks, and never stop learning in open-ended environments.

In this era marked by the advent of AGI, I am also deeply concerned about the value alignment of AI agents, both from a technical perspective and a social science viewpoint.

Greatness cannot be planned, so I play with joyful explorations!

News

Selected Publications [Google Scholar]

  1. ICLR 2024
    Guozheng Ma*, Lu Li*, Sen Zhang, Zixuan Liu, Zhen Wang, Yixin Chen, Li Shen, Xueqian Wang, Dacheng Tao
    International Conference on Learning Representations (ICLR), 2024.

  2. NeurIPS 2023
    Guozheng Ma, Linrui Zhang, Haoyu Wang, Lu Li, Zilin Wang, Zhen Wang, Li Shen, Xueqian Wang, Dacheng Tao
    Neural Information Processing Systems (NeurIPS), 2023.

Invited Talks

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

Honors and Awards

Academic Services

Conference Reviewers

Journal Reviewers

Workshop PCs