Tianjun Zhang

Doctoral student (Ph.D.), EECS Department, UC Berkeley

Email: tianjunz [at] berkeley [dot] edu

I am a fourth-year PhD student in EECS Deparment, UC Berkeley affilicated with the BAIR lab and the RISE lab. I am advised by Prof. Joseph E. Gonzalez. My research interests generally lie in designing better RL algorithms and their application to robotics.

At Berkeley, I am fortunate to work closely with Prof. Sergey Levine and Prof. Jiantao Jiao. I also collaborated closely with Dr. Yuandong Tian from Meta Research and Dr. Bo Dai from Google Brain.

Research Summary

My research has focused on designing better RL algorithms to solve real-world challenges. To be specific, I am working on the following areas:

Data-driven planning: Lap3[1], C-Planning[2]
Representation Learning for RL: SPEDE [3]
Better Exploration Criterion: BeBold [4], MADE[5]

Research opportunities: I am actively looking for students to help with research projects both during the semester and over the summer. If you are interested, please send me an email.

News

New! Two papers were accepted to ICLR 2022: C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks and Multi-objective Optimization by Learning Space Partitions.

New! Two papers were accepted to NeurIPS 2021 Deep RL workshop: C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks and Graph Backup: Data Efficient Backup Exploiting Markovian Data.

New! One paper was accepted to EMNLP 2021: Contrastive Code Representation Learning.

New! Three papers were accepted to NeurIPS 2021: BeBold: Exploration Beyond the Boundary of Explored Regions, MADE: Exploration via Maximizing Deviation from Explored Regions, Learning Space Partitions for Path Planning.

One paper were accepted to NeurIPS 2019: ANODEV2: A Coupled Neural ODE Evolution Framework.

Selected Publications

See Google Scholar for a complete and up-to-date list of publications.

*Equal contribution.