Short Bio

Currently, I am a second-year PhD student at Nanyang Technological University, working under the supervision of Dacheng Tao. Previously, I completed my master's studies and began my research journey at Tsinghua University. Earlier, I obtained my bachelor's degree at Hunan University, where I cherished four wonderful years at the foothills of Yuelu Mountain.

My research goal is to unlock the true potential of Deep Reinforcement Learning toward practical real-world deployment. This requires RL agents capable of offline-online cooperation, handling multiple tasks, and never stopping learning in open-ended environments. To realize this vision, I currently focus on investigating the fundamental challenges inherent in DRL, particularly optimization pathologies, scalability limitations and exploration inefficiencies.

Meanwhile, I view RL as a paradigm for understanding and developing intelligence rather than just a technique. This inspires my interest in exploring its potential across domains, from large reasoning models and embodied agents to psychology and social sciences.

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

News

• [2025.05] Two papers accepted at ICML 2025, discussing DRL scalability on Online RL and Multi-Task DT.
• [2024.08] Kicking off my PhD journey at NTU, Singapore. Keep going on the road!
• [2024.05] Happy to receive ICLR Financial Assistance Award. See you in Vienna!
• [2024.01] Our paper investigating Plasticity Loss in VRL has been accepted by ICLR 2024.
• [2023.12] Our paper about VRL's Generalization got an oral at AAMAS. Congratulations to Lu Li!
• [2023.09] Our paper on 'What makes a effective DA for sample-efficient VRL?' was accepted to NeurIPS 2023.
• Show more
[2023.07] Honored to be named as an AI Safety and Alignment Fellow by Concordia AI!
[2022.10] We released a comprehensive survey of DA in VRL.
[2022.04] Our TLDA was accepted to IJCAI 2022. The fascinating VRL journey began!

Selected Publications [Google Scholar]

Invited Talks

Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages.

• Youth PhD Talk, AI TIME, March 2024 | Recording (in Chinese)
• The 6th AI Academic Forum of Beijing Universities, April 2024       

Honors and Awards

• Excellent Graduates, Beijing, 2024.
• ICLR Financial Assistance Award, 2024.
• ORDOS Scholarship, Tsinghua University, 2023.
• AI Safety and Alignment Fellowship, Concordia AI, 2023.
• Provincial Excellent Graduates, Hunan Province, 2021.
• First Prize of Outstanding Undergraduate Thesis, Hunan University, 2021.
• Weisheng Scholarship, Hunan University, 2020.
• XiongXiaoge Scholarship, Hunan University, 2019
• National Scholarship, Ministry of Education of China, 2019

Academic Services

Conference Reviewers

• International Conference on Machine Learning (ICML) 2024-2025
• Annual Conference on Neural Information Processing Systems (NeurIPS) 2024-2025
• International Conference on Learning Representations (ICLR) 2025
• Conference on Computer Vision and Pattern Recognition (CVPR) 2025
• International Conference on Computer Vision (ICCV) 2025
• European Conference on Computer Vision (ECCV) 2024
• Conference on Lifelong Learning Agents (CoLLAs) 2025

Journal Reviewers

• IEEE Transactions on Image Processing (TIP)

Workshop PCs

• NeurIPS 2025: ARLET Workshop.
• ICLR 2025: MCDC Workshop.
• Show more
NeurIPS 2024: Continual FoMo Workshop, SoLaR Workshop.
ICML 2024: TiFA Workshop, AutoRL Workshop, DMLR Workshop.
NeurIPS 2023: SoLaR Workshop.
ICML 2023: DMLR Workshop.

Workshop Organizers

• NeurIPS 2025: Embodied World Models for Decision Making Workshop.

Community Builders

• Co-founder, Reinforcement Learning Evolution Foundation.