This repository contains code for evaluating the methods proposed in Learning action embeddings for off-policy evaluation.
To get started, we recommend checking the Example.ipynb notebook as it clearly demonstrates benefits of the proposed method from Section 3 and implements everything in a few lines of code. To run the notebook, you only need python 3 with standard machine learning libraries.
To run the other synthetic and real-world experiments in the paper, you might need the AWS account as everything is implemented to run with AWS SageMaker. Depending on the training instance used, the experiments may run for a couple of hours/days.
We also provide commands to run the experiments locally (requires considerable computational resource).