shaodaqian

DML-IV

Implementation of Learning Decision Policies with Instrumental Variables through Double Machine Learning

rl-from-ltl

IJCAI 2023 Sample Efficient Model-free Reinforcement Learning from LTL Specifications with Optimality Guarantees

lipEstimation

ocr-robustness

Robustness Guarantees on Deep Neural Networks for Optical Character Recognition

Transformer

An implementation of the Transformer