Research

Reinforcement Learning

• Multi-Agent Reinforcement Learning models the interaction of multiple agents as a stochastic game. We proposed communication-based methods to coordinate the behaviors of decentralized agents.

• Offline Reinforcement Learning aims to close the gap between real world environment and simulation environment. We are implementing algorithms on real autonomous vehicles for navigation, sensing, etc.

• LLM and Reinforcement Learning builds human-like behaviors by interacting with LLM such as GPT-3.

Data Mining

• Single cell ATAC clustering is to cluster the single cell ATAC data, which is high-dimension, sparse with lots of dropouts. We employ AI methods to analyze the cells.

• Information Diffusion Prediction is to predict the information cascade with historical data. We adopted cascade structure as the main feature for prediction.