Zechu (Steven) Li

I am a PhD student at PEARL Lab advised by Prof. Georgia Chalvatzaki from Oct 2024. My research interest lies in reinforcement learning, especially its applications (e.g., robotics, finance, and transportation) and high-performance and scalable systems.

Prior to this, I was a visiting researcher at MIT CSAIL, advised by Prof. Pulkit Agrawal, where I conducted research on massively parallel simulation and sim-to-real in robotics.

I received my bachelor's degree from Columbia University in May 2022, majoring in computer science. During my undergraduate studies, I was fortunate to work with Prof. Xiaodong Wang, Prof. Anwar Walid and Prof. Sharon (Xuan) Di.

An agentic framework that automates the simulation-side workflow for robot reinforcement learning through harness engineering.

An RL-based data-generation pipeline for language-conditioned bimanual arm-hand manipulation.

A novel RL framework that explicitly leverages the inherent morphological symmetry in bimanual robotic systems to enable ambidextrous control.

A novel diffusion-based maximum entropy algorithm that achieves SOTA performance against both diffusion-based and non-diffusion methods.

A novel actor-critic algorithm that learns multimodal policies as diffusion models from scratch while maintaining versatile behaviors.

A system for robustifying real-world imitation learning policies via reinforcement learning in "digital twin" simulation environments constructed on the fly from small amounts of real-world data.

A novel parallel Q-learning framework that scales off-policy learning to 10000+ parallel environments.

A homomorphic matrix completion algorithm that satisfies the differential privacy property and reduces the best-known error bound to EXACT recovery at a price of more samples.

The first open-source framework to show the great potential of financial reinforcement learning.

A massively parallel library for cloud-native deep reinforcement learning (DRL) applications.

As a leader of this project, I have been contributing to

• develop a series of large-scale training frameworks,
• implemente SOTA algorithms and techniques,
• build the documentation website.

• ElegantRL: Much More Stable Deep Reinforcement Learning Algorithms than Stable-Baseline3,
  MLearning.ai, Mar. 3, 2022.
• ElegantRL-Podracer: A Scalable and Elastic Library for Cloud-Native Deep Reinforcement Learning,
  Towards data science, Dec. 11, 2021.
• ElegantRL: Mastering PPO Algorithms,
  Towards data science, May. 3, 2021.
• ElegantRL Demo: Stock Trading Using DDPG (Part II),
  MLearning.ai, Apr. 19, 2021.
• ElegantRL Demo: Stock Trading Using DDPG (Part I),
  MLearning.ai, Mar. 28, 2021.
• ElegantRL-Helloworld: A Lightweight and Stable Deep Reinforcement Learning Library,
  Towards data science, Mar. 4, 2021.

This chapter takes a practical approach to seek a better efficiency-accuracy trade-off, which utilizes high performance tensor decompositions to compress and accelerate neural networks by exploiting low-rank structures of the network weight matrix.

This guy makes a nice webpage.