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
280
Towards Assessing and Benchmarking Risk-Return Tradeoff of OPE （日本語版）
aiueola
0
300
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
360
Off-Policy Evaluation of Ranking Policies under Diverse User Behavior
aiueola
1
300
Off-Policy Evaluation of Ranking Policies under Diverse User Behavior (日本語版)
aiueola
0
560
海外大学院留学説明会@東工大 2023夏 事前共有資料
aiueola
1
3.3k
OFRL: Designing an Offline Reinforcement Learning and Policy Evaluation Platform from Practical Perspectives
aiueola
0
690
Policy-Adaptive Estimator Selection for Off-Policy Evaluation
aiueola
0
960
Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model
aiueola
2
510
Accelerating Offline RL Application in Real Time Bidding and Recommendation: Potential Use of Simulation
aiueola
1
500
Evaluating the Robustness of Off Policy Evaluation
aiueola
1
460
Offline Reinforcement Learning
aiueola
11
22k
The Multi-Armed Bandit Problem and Its Solutions
aiueola
0
240
Reinforcement Learning and Game Theory
aiueola
2
850

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