Publications

Whom Do We Prefer to Learn From in Observational Reinforcement Learning?

Gota Morishita, Carsten Murawski, Nitin Yadav, and Shinsuke Suzuki

PLoS Computational Biology, 2025

[paper]

Dual Learning Algorithm for Delayed Conversions 

Yuta Saito, Gota Morishita, Shota Yasui

In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval 

(short paper acceptance rate 153/507 = 30.2% )

[arXiv]

A Feedback Shift Correction in Predicting Conversion Rates under Delayed Feedback

Shota Yasui*, Gota Morishita*, Komei Fujita, Masashi Shibata (*equally contributed)

Proceedings of The Web Conference 2020 (WWW '20), April 20--24, 2020, Taipei, Taiwan 

(Oral presentation) 

(short paper acceptance rate 98/397 = 24.7%)

[arXiv]

Online Learning for Bidding Agent under First Price Auction

Gota Morishita*, Kenshi Abe*, Kazuhisa Ogawa, Yusuke Kaneko (equally contributed)

AAAI Workshop on Reinforcement Learning in Games, New York, New York USA, Feburary 7-12 2020

[pdf]

Unbiased CVR Prediction from Biased Conversions in Display Advertising

Yuta Saito, Gota Morishita, Shota Yasui

NeurIPS Workshop on Causal Machine Learning, Vancouver, British Columbia, Canada, Dec. 14, 2019

[arXiv]