Guozheng Ma

I’m Guozheng Ma, a PhD student at Nanyang Technological University, advised by Dacheng Tao. Previously, I completed my master’s studies at Tsinghua University and my bachelor’s degree at Hunan University.

My research focuses on deep reinforcement learning: how agents can learn efficiently, scale, and keep adapting in open-ended environments. I study optimization, network sparsity, plasticity, and the interplay between offline knowledge and online experience. More broadly, I’m interested in RL as a way to understand and develop intelligence.

An illustrated portrait of Guozheng Ma An illustrated portrait of Guozheng Ma

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

Selected Research

All Publications

9 papers & technical reports

Preprint

2026

From Discovery to Mastery: Reallocating the Replay Budget in Massively Parallel RL

First author

Guozheng Ma, Qi Zhao, Lu Li, Zilin Wang, Pierre-Luc Bacon, Dacheng Tao

Discovering successful behavior does not guarantee that a policy learns to reproduce it. REAP reallocates an existing replay budget toward high-return experience, improving learning across 48 control tasks without increasing interaction or update budgets.

Technical report

2026

ACE-CaP-0: Real-World Code-as-Policies in the Era of Experience

Core contributor

ACE-CaP Team · ACE Robotics

Core contributors: Changxu Wei, Yunpeng Qing, Guozheng Ma

A coding agent requests robot demonstrations and simulation on demand, developing code policies through real-world feedback. The resulting programs are frozen for evaluation and run without a human or coding agent in the loop.

Drag to explore or use the arrow keys

01 / 09