Tianying Ji

About Me

Hi! I am currently a PhD student at the State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, advised by Prof. Fuchun Sun, and work closely with Huazhe Xu (IIIS) and Xianyuan Zhan (AIR). I obtained my bachelor degree from Department of Computer Science and Technology, Tsinghua University in 2020.

I'm broadly interested in research on Reinforcement Learning and Robotics, currently especially in exploring general-purpose RL for real-robot tasks.

I'm happy to collaborate with graduate/undergraduate students and welcome virtual coffee chats. Drop me an email if you're interested in exploring efficient, robust RL, real-world/simulation robotic learning, or any other exciting research topics.

News

Selected Publications & Preprints

* denotes equal contributions; § indicates involvement in mentoring.

ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization
Tianying Ji*, Yongyuan Liang*, Yan Zeng, Yu Luo, Guowei Xu, Jiawei Guo, Ruijie Zheng, Furong Huang, Fuchun Sun, Huazhe Xu
ICML, 2024 (Oral)
Project page / Paper link / Code / bibtex

Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic
Tianying Ji, Yu Luo, Fuchun Sun, Xianyuan Zhan, Jianwei Zhang, Huazhe Xu
ICML, 2024
Project page / Paper link / Code / bibtex

OMPO: A Unified Framework for RL under Policy and Dynamics Shifts
Yu Luo, Tianying Ji, Fuchun Sun, Jianwei Zhang, Huazhe Xu, Xianyuan Zhan
ICML, 2024 (Oral)
Paper link / Code / bibtex

Offline-Boosted Actor-Critic:Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL
Yu Luo, Tianying Ji, Fuchun Sun, Jianwei Zhang, Huazhe Xu, Xianyuan Zhan
ICML, 2024
Project page / Paper link / Code / bibtex

Goal-Conditioned Hierarchical Reinforcement Learning With High-Level Model Approximation
Yu Luo, Tianying Ji, Fuchun Sun, Huaping Liu, Jianwei Zhang, Mingxuan Jing, Wenbing Huang
IEEE Transactions on Neural Networks and Learning Systems
Paper Link / bibtex

H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps
Haoyi Niu*, Tianying Ji*, Bingqi Liu, Haocheng Zhao, Xiangyu Zhu, Jianying Zheng, Pengfei Huang, Guyue Zhou, Jianming Hu, Xianyuan Zhan
DMLR @ ICLR 2024
Project page / Paper link / bibtex

DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
Guowei Xu*, Ruijie Zheng*, Yongyuan Liang*, Xiyao Wang, Zhecheng Yuan, Tianying Ji, Yu Luo, Xiaoyu Liu, Jiaxin Yuan, Pu Hua, Shuzhen Li, Yanjie Ze, Hal Daumé III, Furong Huang, Huazhe Xu
ICLR, 2024 (Spotlight)
CoRL Workshop (CoRL23-WS-Deployable), 2023
Project page / Paper link / Code / bibtex

When to Update Your Model: Constrained Model-based Reinforcement Learning
Tianying Ji, Yu Luo, Fuchun Sun, Mingxuan Jing, Fengxiang He, Wenbing Huang
NeurIPS, 2022 (Spotlight)
Project page / Paper link / Code / bibtex

BDAC: A Behavior-aware Dynamic Adaptive Configuration on DHCP in Wireless LANs
Congcong Miao, Jilong Wang, Tianying Ji, Hui Wang, Chao Xu, Fenghua Li, Fengyuan Ren
IEEE 27th International Conference on Network Protocols (ICNP), 2019
paper link / bibtex

Professional Service

Conference Reviewer: NeurIPS(2023,2024), ICML(2024), ICLR(2024), IJCAI(2024)