Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation
arXiv:2008.07146
Abstract
Off-policy evaluation (OPE) aims to estimate the performance of hypothetical policies using data generated by a different policy. Because of its huge potential impact in practice, there has been growing research interest in this field. There is, however, no real-world public dataset that enables the evaluation of OPE, making its experimental studies unrealistic and irreproducible. With the goal of enabling realistic and reproducible OPE research, we present Open Bandit Dataset, a public logged bandit dataset collected on a large-scale fashion e-commerce platform, ZOZOTOWN. Our dataset is unique in that it contains a set of multiple logged bandit datasets collected by running different policies on the same platform. This enables experimental comparisons of different OPE estimators for the first time. We also develop Python software called Open Bandit Pipeline to streamline and standardize the implementation of batch bandit algorithms and OPE. Our open data and software will contribute to fair and transparent OPE research and help the community identify fruitful research directions. We provide extensive benchmark experiments of existing OPE estimators using our dataset and software. The results open up essential challenges and new avenues for future OPE research.
Accepted at NeurIPS2021 Datasets and Benchmarks Track
References in corpus (9)
- Open Graph Benchmark: Datasets for Machine Learning on Graphs
- Benchmarking Graph Neural Networks
- Learning from Logged Implicit Exploration Data
- Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning
- Counterfactual Evaluation of Slate Recommendations with Sequential Reward Interactions
- Evaluating the Robustness of Off-Policy Evaluation
- Benchmarks for Deep Off-Policy Evaluation
- A Practical Guide of Off-Policy Evaluation for Bandit Problems
- Finite-time Analysis of Globally Nonstationary Multi-Armed Bandits