Z(he)²

Zhe He

I am a PhD student in Computer Science at the University of Macau, advised by Meng Qu and Steven Morad. I received my MSc (Thesis) in Artificial Intelligence from the same university under the supervision of Steven Morad.

I often bring reflections from everyday life into my research. I enjoy thinking about how we think and learn, and this curiosity drew me to reinforcement learning.

My interests span streaming reinforcement learning, continual learning, and meta-learning. I study how agents learn from ongoing interaction and improve their ability to learn. My current work focuses on learning mechanisms in streaming RL and memory models for partially observable environments.

Zhe He

Publications

Investigating Memory in Model-Free RL with POPGym Arcade

Zekang Wang*, Zhe He*, Borong Zhang, Edan Toledo, Steven Morad

* Equal Contribution

ICML 2026 (Spotlight)

Experience

Updates