Scholar
Zechu Li
Google Scholar ID: FI_6by0AAAAJ
Columbia University, MIT
Citations & Impact
Citations
266
H-index
7
i10-index
6
Publications
12
Co-authors
7
list available
Publications
Resume (English only)
Academic Achievements
- Published 'Morphologically Symmetric Reinforcement Learning for Ambidextrous Bimanual Manipulation' at CoRL 2025
- Published 'DIME: Diffusion-Based Maximum Entropy Reinforcement Learning' at ICML 2025
- Published 'Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient' at NeurIPS 2024
- Published 'Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation' at Robotics: Science and Systems (RSS) 2024
- Published 'Parallel Q-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation' at ICML 2023
- Published 'Homomorphic Matrix Completion' at NeurIPS 2022
- Led the open-source project FinRL: the first framework demonstrating the potential of financial reinforcement learning
- Led the open-source project ElegantRL “小雅”: a massively parallel library for cloud-native deep reinforcement learning
- Has authored technical blog posts since March 2021 on topics including ElegantRL stability, PPO algorithms, and the Podracer library
