Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy
Evaluation

v1v2v3 (latest)

Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation

30 November 2023

Haruka Kiyohara

Kazuhide Nakata

ArXiv (abs)PDF HTML Github (122★)

Papers citing "Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation"

10 / 10 papers shown

Title
DOLCE: Decomposing Off-Policy Evaluation/Learning into Lagged and Current Effects Shu Tamano Masanori Nojima OffRL 202 0 0 02 May 2025
Prompt Optimization with Logged Bandit Data Haruka Kiyohara Daniel Yiming Cao Yuta Saito Thorsten Joachims 229 0 0 03 Apr 2025
Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits Tatsuhiro Shimizu Koichi Tanaka Ren Kishimoto Haruka Kiyohara Masahiro Nomura Yuta Saito CML OffRL 88 1 0 20 Aug 2024
Balancing Immediate Revenue and Future Off-Policy Evaluation in Coupon Allocation Naoki Nishimura Ken Kobayashi Kazuhide Nakata OffRL 40 0 0 06 Jul 2024
Long-term Off-Policy Evaluation and Learning Yuta Saito Himan Abdollahpouri Jesse Anderton Ben Carterette M. Lalmas OffRL 80 8 0 24 Apr 2024
Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It Yuta Saito Masahiro Nomura OffRL 92 3 0 23 Apr 2024
POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition Yuta Saito Jihan Yao Thorsten Joachims OffRL 102 9 0 09 Feb 2024
Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction Haruka Kiyohara Masahiro Nomura Yuta Saito 89 8 0 03 Feb 2024
SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation Haruka Kiyohara Ren Kishimoto K. Kawakami Ken Kobayashi Kazuhide Nakata Yuta Saito OffRL ELM 93 4 0 30 Nov 2023
Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation Yuta Saito Shunsuke Aihara Megumi Matsutani Yusuke Narita OffRL 201 75 0 17 Aug 2020

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.