Scholar
Hongyao Tang
Google Scholar ID: yIqzRH4AAAAJ
Mila/UdeM
Citations & Impact
Citations
1,441
H-index
17
i10-index
19
Publications
20
Co-authors
26
list available
Publications
Resume (English only)
Academic Achievements
- Released Embodied Arena, a comprehensive, unified, and evolving evaluation platform for Embodied AI; Four papers accepted to NeurIPS 2025 on LLM-driven reward function design, multi-objective RL, offline RL, and EDA floorplanning; One paper accepted to RLC 2025 on efficient cross-morphology adaptation; Two papers accepted to ICML 2025 on continual RL and LLM-driven reward design.
Research Experience
- 2025.01 - Present, Associate Research Fellow, TJU RL Lab, College of Intelligence and Computing, Tianjin University; 2023.11 - 2024.12, Postdoctoral Research Fellow, Robotics and Embodied AI Lab (REAL), Mila/UdeM (worked with Glen Berseth); 2020.05 - 2023.04, DRL Researcher (Intern), Noah's Ark Lab, Huawei (worked with Chen Chen and Zhentao Tang); 2019.09 - 2020.04, AI Researcher (Intern), Quantum Lab, Tencent (worked with Guangyong Chen); 2018.07 - 2018.10, DRL Researcher (Intern), Fuxi AI Lab, NetEase (worked with Tangjie Lv).
Education
- Ph.D.: 2019.09 - 2023.06, College of Intelligence and Computing, Tianjin University, advised by Prof. Jianye Hao and Prof. Zhaopeng Meng; Master's Degree: 2017.09 - 2019.07, College of Intelligence and Computing, Tianjin University, advised by Prof. Jianye Hao and Prof. Li Wang; Bachelor's Degree: 2013.09 - 2017.07, School of Software Engineering, Tianjin University.
Background
- Research interests include unveiling the learning dynamics of Deep Reinforcement Learning (DRL) and realizing new approaches/paradigms for efficient, performant, and generalizable agents. Current research focus is on Learning under Nonstationarity, specifically studying Continual RL and RL problems in LLMs and embodied intelligence. Also interested in Meta RL, MARL, Offline RL, Machine Unlearning, etc.
Miscellany
- Prospective students (master, ph.d., RA, etc.) and collaboration partners are welcome to contact me via my email or through the homepage of TJU RL Lab.
