[2026-Oct-07] An Overview of Robot Learning & My Academic Trajectory and Philosophy

Institute of Information Systems and Applications

Speaker:

Prof. Shao-Hua Sun

Assistant Professor of the Department of Electrical Engineering at National Taiwan University

Topic:

An Overview of Robot Learning & My Academic Trajectory and Philosophy ​

Date:

13:20-15:00 Wednesday 07-Oct-2026

Location:

Delta 103

Hosted by:

Prof. Yi-Shin Chen

Abstract

This talk consists of two parts: an overview of robot learning and a personal reflection on my career choices, life philosophy, and the broader purpose of research and higher education.
In the first part, I will provide an overview of robot learning, centering on the fundamental goal of developing generalist agents capable of executing novel, diverse tasks within unstructured environments. I will review two core paradigms—Reinforcement Learning (RL) and Imitation Learning (IL)—examining their underlying formulations, representative applications, and key technical bottlenecks. I will highlight my research agenda along two primary frontiers: program-guided robot learning and imitation learning with diffusion models.

In the second part, I step back from the technical details to reflect on my own academic trajectory, from undergraduate training in electrical engineering at National Taiwan University, through doctoral study in computer science at the University of Southern California, to my return to Taiwan as a faculty member. Through this journey, I articulate a personal philosophy centered on maximizing the integral of joyful experiences over a lifetime. Then, I will share some practical principles for cultivating a happy and sustainable life. Finally, I will discuss my views on the purpose of academic research training and the role higher education should play in this rapidly changing world.

Bio.

Shao-Hua Sun is an Assistant Professor in the Department of Electrical Engineering at National Taiwan University (NTU). He received his Ph.D. from the University of Southern California and his B.S. from NTU. His research spans machine learning, robot learning, reinforcement learning, and program synthesis. His work has been published in leading venues, including NeurIPS, ICML, CoRL, ICLR, etc. He has organized tutorials and workshops at NeurIPS, ICML, RLC, and CoRL. He has been awarded the MOE Yushan Young Fellow (教育部玉山青年學者), the NSTC Ta-You Wu Memorial Award (國科會吳大猷先生紀念獎), and the IICM K. T. Li Young Researcher Award (中華民國資訊學會李國鼎青年研究獎).

 

All faculty and students are welcome to join.