Publications

BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinfocement Learning
OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning
Safety-aware Causal Representation for Trustworthy Offline Reinforcement Learning in Autonomous Driving
Datasets and Benchmarks for Offline Safe Reinforcement Learning
Rethinking Controllable Variational Autoencoders
Controllable and Diverse Text Generation in E-commerce