paper-with-me

Papers

Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation

2020-08-17 · Yuta Saito, Shunsuke Aihara, Megumi Matsutani, Yusuke Narita

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.

📄 PDF Abstract BibTeX arXiv:2008.07146

Code (4)

st-tech/zr-obp 공식 구현
RetailMarketingAI/retailsynth-agentsim jax
han20192019/newRL
usaito/obp-demo

Tasks

Off-policy evaluation

Similar Papers 제목 키워드 기반

Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI

2025-11-25 · Xinhao Liu, Jiaqi Li, Youming Deng, Ruxin Chen 외 arxiv

Reproducible closed-loop evaluation remains a major bottleneck in Embodied AI such as visual navigation. A promising path forward is high-fidelity simulation that combines photorealistic sensor rendering with geometrical…

Novel View Synthesis3D ReconstructionVisual Navigation

Temporal Graph Benchmark for Machine Learning on Temporal Graphs

2023-07-03 · NeurIPS 2023 11 · Shenyang Huang, Farimah Poursafaei, Jacob Danovitch, Matthias Fey 외

We present the Temporal Graph Benchmark (TGB), a collection of challenging and diverse benchmark datasets for realistic, reproducible, and robust evaluation of machine learning models on temporal graphs. TGB datasets are…

Node Property PredictionProperty Prediction

Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learning

2021-11-08 · Qinkai Zheng, Xu Zou, Yuxiao Dong, Yukuo Cen 외

Adversarial attacks on graphs have posed a major threat to the robustness of graph machine learning (GML) models. Naturally, there is an ever-escalating arms race between attackers and defenders. However, the strategies …

Adversarial RobustnessBenchmarkingBIG-bench Machine Learning

Human Mobility Datasets Enriched With Contextual and Social Dimensions

2025-09-26 · Chiara Pugliese, Francesco Lettich, Guido Rocchietti, Chiara Renso 외 arxiv

In this resource paper, we present two publicly available datasets of semantically enriched human trajectories, together with the pipeline to build them. The trajectories are publicly available GPS traces retrieved from …

Extending Open Bandit Pipeline to Simulate Industry Challenges

2022-09-09 · Bram van den Akker, Niklas Weber, Felipe Moraes, Dmitri Goldenberg

Bandit algorithms are often used in the e-commerce industry to train Machine Learning (ML) systems when pre-labeled data is unavailable. However, the industry setting poses various challenges that make implementing bandi…