Off-Policy Evaluation for Large Action Spaces via Policy Convolution

Author:

Sachdeva Noveen1ORCID,Wang Lequn2ORCID,Liang Dawen2ORCID,Kallus Nathan3ORCID,McAuley Julian1ORCID

Affiliation:

1. University of California, San Diego, La Jolla, CA, USA

2. Netflix, Los Gatos, CA, USA

3. Netflix & Cornell University, Los Gatos, CA, USA

Publisher

ACM

Reference47 articles.

1. Jacob Buckman, Carles Gelada, and Marc G Bellemare. The importance of pessimism in ?xed-dataset policy optimization. In International Conference on Learning Representations, 2021.

2. Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. A simple framework for contrastive learning of visual representations. In International conference on machine learning, pages 1597--1607. PMLR, 2020.

3. Doubly Robust Policy Evaluation and Optimization

4. Miroslav Dudík, John Langford, and Lihong Li. Doubly robust policy evaluation and learning. In Proceedings of the 28th International Conference on International Conference on Machine Learning, ICML'11, 2011.

5. Mehrdad Farajtabar, Yinlam Chow, and Mohammad Ghavamzadeh. More robust doubly robust off-policy evaluation. In International Conference on Machine Learning, pages 1447--1456. PMLR, 2018.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3