This is the code of our paper "Policy Learning for Balancing Short-Term and Long-Term Rewards".

The "data_generateJOBS" and "data_generateIHDP" files include the data generation process for JOBS and IHDP datasets, respectively. 

We put our final data in the data folder, named "ihdp1_train_data" and "JOBS_train_data". 

To recover our experimental results, please refer to main_idhp.py and main_job files. Each of them corresponds to one dataset.