Doubly Robust Off-Policy Value Evaluation for Reinforcement Learning. Jiang, N. & Li, L. In International Conference on Machine Learning, pages 652-661. Paper abstract bibtex We study the problem of off-policy value evaluation in reinforcement learning (RL), where one aims to estimate the value of a new policy based on data collected by a different policy. This problem ...
@inproceedings{jiangDoublyRobustOffpolicy2016,
langid = {english},
title = {Doubly {{Robust Off}}-Policy {{Value Evaluation}} for {{Reinforcement Learning}}},
url = {http://proceedings.mlr.press/v48/jiang16.html},
abstract = {We study the problem of off-policy value evaluation in reinforcement learning (RL), where one aims to estimate the value of a new policy based on data collected by a different policy. This problem ...},
eventtitle = {International {{Conference}} on {{Machine Learning}}},
booktitle = {International {{Conference}} on {{Machine Learning}}},
urldate = {2019-05-17},
date = {2016-06-11},
pages = {652-661},
author = {Jiang, Nan and Li, Lihong},
file = {/home/dimitri/Nextcloud/Zotero/storage/6B6SSYEQ/jiang16-supp.pdf;/home/dimitri/Nextcloud/Zotero/storage/IBUZU3LH/Jiang and Li - 2016 - Doubly Robust Off-policy Value Evaluation for Rein.pdf;/home/dimitri/Nextcloud/Zotero/storage/XRBVCV63/jiang16.html}
}
Downloads: 0
{"_id":"AH8sjpjQgP4SC7STJ","bibbaseid":"jiang-li-doublyrobustoffpolicyvalueevaluationforreinforcementlearning","authorIDs":[],"author_short":["Jiang, N.","Li, L."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","langid":"english","title":"Doubly Robust Off-Policy Value Evaluation for Reinforcement Learning","url":"http://proceedings.mlr.press/v48/jiang16.html","abstract":"We study the problem of off-policy value evaluation in reinforcement learning (RL), where one aims to estimate the value of a new policy based on data collected by a different policy. This problem ...","eventtitle":"International Conference on Machine Learning","booktitle":"International Conference on Machine Learning","urldate":"2019-05-17","date":"2016-06-11","pages":"652-661","author":[{"propositions":[],"lastnames":["Jiang"],"firstnames":["Nan"],"suffixes":[]},{"propositions":[],"lastnames":["Li"],"firstnames":["Lihong"],"suffixes":[]}],"file":"/home/dimitri/Nextcloud/Zotero/storage/6B6SSYEQ/jiang16-supp.pdf;/home/dimitri/Nextcloud/Zotero/storage/IBUZU3LH/Jiang and Li - 2016 - Doubly Robust Off-policy Value Evaluation for Rein.pdf;/home/dimitri/Nextcloud/Zotero/storage/XRBVCV63/jiang16.html","bibtex":"@inproceedings{jiangDoublyRobustOffpolicy2016,\n langid = {english},\n title = {Doubly {{Robust Off}}-Policy {{Value Evaluation}} for {{Reinforcement Learning}}},\n url = {http://proceedings.mlr.press/v48/jiang16.html},\n abstract = {We study the problem of off-policy value evaluation in reinforcement learning (RL), where one aims to estimate the value of a new policy based on data collected by a different policy. This problem ...},\n eventtitle = {International {{Conference}} on {{Machine Learning}}},\n booktitle = {International {{Conference}} on {{Machine Learning}}},\n urldate = {2019-05-17},\n date = {2016-06-11},\n pages = {652-661},\n author = {Jiang, Nan and Li, Lihong},\n file = {/home/dimitri/Nextcloud/Zotero/storage/6B6SSYEQ/jiang16-supp.pdf;/home/dimitri/Nextcloud/Zotero/storage/IBUZU3LH/Jiang and Li - 2016 - Doubly Robust Off-policy Value Evaluation for Rein.pdf;/home/dimitri/Nextcloud/Zotero/storage/XRBVCV63/jiang16.html}\n}\n\n","author_short":["Jiang, N.","Li, L."],"key":"jiangDoublyRobustOffpolicy2016","id":"jiangDoublyRobustOffpolicy2016","bibbaseid":"jiang-li-doublyrobustoffpolicyvalueevaluationforreinforcementlearning","role":"author","urls":{"Paper":"http://proceedings.mlr.press/v48/jiang16.html"},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/dlozeve/newblog/master/bib/all.bib","creationDate":"2020-01-08T20:39:39.364Z","downloads":0,"keywords":[],"search_terms":["doubly","robust","policy","value","evaluation","reinforcement","learning","jiang","li"],"title":"Doubly Robust Off-Policy Value Evaluation for Reinforcement Learning","year":null,"dataSources":["3XqdvqRE7zuX4cm8m"]}