Lock in $30 Savings on PRO—Offer Ends Soon! ⏳
Featured
Business
Design
Education
How-to & DIY
Marketing & SEO
Programming
Research
Science
Storyboards
Technology
Avatar for Haruka Kiyohara

Haruka Kiyohara

harukakiyohara_
0 Stars

CS Ph.D. student at Cornell / B.Eng. from Tokyo Tech / interested in (offline) reinforcement learning and off-policy evaluation / 日本語 https://speakerdeck.com/aiueola

Decks

[A-exam'25] Data-efficiency, steerability, and adaptability for personalized decisions at scale
Avatar for Haruka Kiyohara harukakiyohara_
0
14
[Guest lecture Fall'25] Off-policy evaluation and learning in "CS6784: ML in feedback systems" at Cornell
Avatar for Haruka Kiyohara harukakiyohara_
0
36
[RecSys'25] An Off-Policy Learning Approach for Steering Sentence Generation towards Personalization
Avatar for Haruka Kiyohara harukakiyohara_
0
50
[ICML'25] Policy Design for Two-sided Platforms with Participation Dynamics
Avatar for Haruka Kiyohara harukakiyohara_
0
74
[WWW'24] Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction
Avatar for Haruka Kiyohara harukakiyohara_
0
200
[ICLR'24] Towards Assessing and Benchmarking Risk-Return Tradeoff of OPE
Avatar for Haruka Kiyohara harukakiyohara_
0
1.4k
[arXiv'23] SCOPE-RL: A Python Library for Offline RL and Off-Policy Evaluation
Avatar for Haruka Kiyohara harukakiyohara_
0
480
[KDD'23] Off-Policy Evaluation of Ranking Policies under Diverse User Behaviors
Avatar for Haruka Kiyohara harukakiyohara_
0
210
[AAAI'23] Policy-Adaptive Estimator Selection for Off-Policy Evaluation
Avatar for Haruka Kiyohara harukakiyohara_
0
110
[WSDM'22] Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model
Avatar for Haruka Kiyohara harukakiyohara_
0
120
[RecSys'21] Evaluating the Robustness of Off-Policy Evaluation
Avatar for Haruka Kiyohara harukakiyohara_
0
100

Speaker Deck Pro: Add privacy options and schedule the publishing of your decks Upgrade