news (archived)
Here are the archives of (relatively) important news:
[2024.01, paper] Our paper "Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction" has been accepted to WebConf2024. See you in Singapore!
[2024.01, paper] Our paper "Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation" has been accepted to ICLR2024. This paper was also featured by the TokyoTech news. See you in New Orleans!
[2023.11, paper, open-source] Our twin papers: "Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation" (link) and "SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation" (link) are now on arXiv! We present a new evaluation metric and open-source software (GitHub, PyPI, readthedocs) for OPE. Feel free to star and folk!
[2023.09, paper] Our paper "Future-Dependent Value-Based Off-Policy Evaluation in POMDPs" has been accepted to NeurIPS2023. See you in New Orleans!
[2023.08, updates, fellowship] I joined the Cornell CS Ph.D. program. I appreciate the financial support of the Funai Overseas Scholarship for the first two academic years. Looking forward to my new journey at Cornell!
[2023.05, paper] Our paper "Off-Policy Evaluation of Ranking Policies under Diverse User Behavior" has been accepted to KDD2023. See you in Long Beach, CA!
[2023.03, updates, award] I graduated from Tokyo Institute of Technology with a B.Eng (Industrial Engineering and Economics) and honor of Excellent Student Award! I am grateful for all the amazing people I met and the wonderful opportunities I could have during my undergraduate study.
[2022.11, paper] Our paper "Policy-Adaptive Estimator Selection for Off-Policy Evaluation" has been accepted to AAAI2023. See you in Washington DC!
[2022.08, paper] Four papers have been accepted to CONSEQUENCES+REVEAL WS @ RecSys2022. Among them, two papers have been selected for oral presentation, "OFRL: Designing an Offline Reinforcement Learning and Policy Evaluation Platform from Practical Perspectives" at REVEAL (Day 1). "Improving Accuracy of Off-Policy Evaluation via Policy Adaptive Estimator Selection" at CONSEQUENCES (Day 2). See you in Seattle!
[2022.02, paper, award] Our paper "Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model" has been honored as one of the Best Paper Award Runner-Ups at WSDM2022! I really appreciate and congratulate all my co-authors.
[2021.02, open-source] We publicized awesome-offline-rl repository and collect papers about Offline RL and OPE. Check it out!