Haruka Kiyohara

24 papers A* 6A 4Journal 14
YearRankTypeTitle / Venue / Authors
2025 A conf
An Off-Policy Learning Approach for Steering Sentence Generation towards Personalization.
RecSys
Haruka Kiyohara, Daniel Yiming Cao, Yuta Saito, Thorsten Joachims
2025 A* conf
Policy Design for Two-sided Platforms with Participation Dynamics.
ICML
Haruka Kiyohara, Fan Yao, Sarah Dean
2025 J jnl
Policy Design for Two-sided Platforms with Participation Dynamics.
CoRR
Haruka Kiyohara, Fan Yao, Sarah Dean
2025 J jnl
Prompt Optimization with Logged Bandit Data.
CoRR
Haruka Kiyohara, Daniel Yiming Cao, Yuta Saito, Thorsten Joachims
2025 J jnl
Safely Exploring Novel Actions in Recommender Systems via Deployment-Efficient Policy Learning.
CoRR
Haruka Kiyohara, Yusuke Narita, Yuta Saito, Kei Tateno, Takuma Udagawa
2024 A conf
Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits.
RecSys
Tatsuhiro Shimizu, Koichi Tanaka, Ren Kishimoto, Haruka Kiyohara, Masahiro Nomura, Yuta Saito
2024 J jnl
Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits.
CoRR
Tatsuhiro Shimizu, Koichi Tanaka, Ren Kishimoto, Haruka Kiyohara, Masahiro Nomura, Yuta Saito
2024 A* conf
Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction.
WWW
Haruka Kiyohara, Masahiro Nomura, Yuta Saito
2024 J jnl
Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction.
CoRR
Haruka Kiyohara, Masahiro Nomura, Yuta Saito
2024 A* conf
Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation.
ICLR
Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito
2023 A* conf
Future-Dependent Value-Based Off-Policy Evaluation in POMDPs.
NeurIPS
Masatoshi Uehara, Haruka Kiyohara, Andrew Bennett, Victor Chernozhukov, Nan Jiang, Nathan Kallus, Chengchun Shi, Wen Sun
2023 A* conf
Off-Policy Evaluation of Ranking Policies under Diverse User Behavior.
KDD
Haruka Kiyohara, Masatoshi Uehara, Yusuke Narita, Nobuyuki Shimizu, Yasuo Yamamoto, Yuta Saito
2023 J jnl
Off-Policy Evaluation of Ranking Policies under Diverse User Behavior.
CoRR
Haruka Kiyohara, Masatoshi Uehara, Yusuke Narita, Nobuyuki Shimizu, Yasuo Yamamoto, Yuta Saito
2023 A* conf
Policy-Adaptive Estimator Selection for Off-Policy Evaluation.
AAAI
Takuma Udagawa, Haruka Kiyohara, Yusuke Narita, Yuta Saito, Kei Tateno
2023 J jnl
SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation.
CoRR
Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito
2023 J jnl
Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation.
CoRR
Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito
2022 A conf
Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model.
WSDM
Haruka Kiyohara, Yuta Saito, Tatsuya Matsuhiro, Yusuke Narita, Nobuyuki Shimizu, Yasuo Yamamoto
2022 J jnl
Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model.
CoRR
Haruka Kiyohara, Yuta Saito, Tatsuya Matsuhiro, Yusuke Narita, Nobuyuki Shimizu, Yasuo Yamamoto
2022 J jnl
Future-Dependent Value-Based Off-Policy Evaluation in POMDPs.
CoRR
Masatoshi Uehara, Haruka Kiyohara, Andrew Bennett, Victor Chernozhukov, Nan Jiang, Nathan Kallus, Chengchun Shi, Wen Sun
2022 J jnl
Policy-Adaptive Estimator Selection for Off-Policy Evaluation.
CoRR
Takuma Udagawa, Haruka Kiyohara, Yusuke Narita, Yuta Saito, Kei Tateno
2021 J jnl
Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation.
CoRR
Haruka Kiyohara, Kosuke Kawakami, Yuta Saito
2021 J jnl
Constrained Generalized Additive 2 Model with Consideration of High-Order Interactions.
CoRR
Akihisa Watanabe, Michiya Kuramata, Kaito Majima, Haruka Kiyohara, Kensho Kondo, Kazuhide Nakata
2021 A conf
Evaluating the Robustness of Off-Policy Evaluation.
RecSys
Yuta Saito, Takuma Udagawa, Haruka Kiyohara, Kazuki Mogi, Yusuke Narita, Kei Tateno
2021 J jnl
Evaluating the Robustness of Off-Policy Evaluation.
CoRR
Yuta Saito, Takuma Udagawa, Haruka Kiyohara, Kazuki Mogi, Yusuke Narita, Kei Tateno