Featured
Business
Design
Education
How-to & DIY
Marketing & SEO
Programming
Research
Science
Storyboards
Technology

Haruka Kiyohara

aiueola
0 Stars

Incoming CS Ph.D. student at Cornell / B.Eng. from Tokyo Tech (経営工学) / interested in (offline) reinforcement learning and off-policy evaluation / English https://speakerdeck.com/harukakiyohara_

Decks

Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction（日本語版）
aiueola
0
17
Towards Assessing and Benchmarking Risk-Return Tradeoff of OPE （日本語版）
aiueola
0
59
SCOPE-RL: オフライン強化学習とオフ方策評価のライブラリ
aiueola
0
130
Off-Policy Evaluation of Ranking Policies under Diverse User Behavior (日本語版)
aiueola
0
380
Off-Policy Evaluation of Ranking Policies under Diverse User Behavior
aiueola
1
190
海外大学院留学説明会@東工大 2023夏 事前共有資料
aiueola
1
2.4k
Policy-Adaptive Estimator Selection for Off-Policy Evaluation
aiueola
0
810
OFRL: Designing an Offline Reinforcement Learning and Policy Evaluation Platform from Practical Perspectives
aiueola
0
460
Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model
aiueola
2
410
Accelerating Offline RL Application in Real Time Bidding and Recommendation: Potential Use of Simulation
aiueola
1
430
Evaluating the Robustness of Off Policy Evaluation
aiueola
1
380
Offline Reinforcement Learning
aiueola
12
19k
The Multi-Armed Bandit Problem and Its Solutions
aiueola
0
160
Reinforcement Learning and Game Theory
aiueola
2
750

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