{"id":"https://openalex.org/W3095986187","doi":"https://doi.org/10.1109/tpami.2021.3088063","title":"Batch Reinforcement Learning With a Nonparametric Off-Policy Policy Gradient","display_name":"Batch Reinforcement Learning With a Nonparametric Off-Policy Policy Gradient","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3095986187","doi":"https://doi.org/10.1109/tpami.2021.3088063","mag":"3095986187","pmid":"https://pubmed.ncbi.nlm.nih.gov/34106848"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2021.3088063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3088063","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.14771","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051476305","display_name":"Samuele Tosatto","orcid":"https://orcid.org/0000-0002-5795-9541"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Samuele Tosatto","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, AB, Canada","[Computer Science, University of Alberta, 3158 Edmonton, Alberta, Canada, (e-mail: samuele.tosatto@gmail.com)]"],"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"[Computer Science, University of Alberta, 3158 Edmonton, Alberta, Canada, (e-mail: samuele.tosatto@gmail.com)]","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053233736","display_name":"J. Frederico Carvalho","orcid":"https://orcid.org/0000-0002-8750-0897"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Joao Carvalho","raw_affiliation_strings":["FG Intelligent Autonomous Systems, Technische Universität Darmstadt, Darmstadt, Germany","Computer Science, Technische Universitat Darmstadt, 26536 Darmstadt, Hesse, Germany, (e-mail: joao.carvalho@tu-darmstadt.de)"],"affiliations":[{"raw_affiliation_string":"FG Intelligent Autonomous Systems, Technische Universität Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Computer Science, Technische Universitat Darmstadt, 26536 Darmstadt, Hesse, Germany, (e-mail: joao.carvalho@tu-darmstadt.de)","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["FG Intelligent Autonomous Systems, Technische Universität Darmstadt, Darmstadt, Germany","Computer Science, Technische Universitat Darmstadt, 26536 Darmstadt, Hesse, Germany, (e-mail: mail@jan-peters.net)"],"affiliations":[{"raw_affiliation_string":"FG Intelligent Autonomous Systems, Technische Universität Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Computer Science, Technische Universitat Darmstadt, 26536 Darmstadt, Hesse, Germany, (e-mail: mail@jan-peters.net)","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051476305"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00935749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"44","issue":"10","first_page":"5996","last_page":"6010"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9805999994277954,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","score":0.9789000153541565,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8338966965675354},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.7154507637023926},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6781141757965088},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6743022799491882},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.6617506146430969},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5777450203895569},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5512785911560059},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4774249792098999},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.441921591758728},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.422131210565567},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.41645359992980957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3060624301433563},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19403067231178284},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.18056097626686096},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.08789634704589844},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07638382911682129}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8338966965675354},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.7154507637023926},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6781141757965088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6743022799491882},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.6617506146430969},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5777450203895569},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5512785911560059},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4774249792098999},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.441921591758728},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.422131210565567},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.41645359992980957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3060624301433563},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19403067231178284},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.18056097626686096},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.08789634704589844},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07638382911682129},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tpami.2021.3088063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3088063","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:34106848","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34106848","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:2010.14771","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.14771","pdf_url":"https://arxiv.org/pdf/2010.14771","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3095986187","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2010.14771","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2010.14771","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.14771","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.14771","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.14771","pdf_url":"https://arxiv.org/pdf/2010.14771","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4050404592","display_name":null,"funder_award_id":"640554","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320319558","display_name":"Bosch-Forschungsstiftung","ror":null},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320869","display_name":"Robert Bosch Stiftung","ror":"https://ror.org/012kqkf58"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3095986187.pdf","grobid_xml":"https://content.openalex.org/works/W3095986187.grobid-xml"},"referenced_works_count":105,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W166862392","https://openalex.org/W1499669280","https://openalex.org/W1528215793","https://openalex.org/W1547925194","https://openalex.org/W1550698229","https://openalex.org/W1571975558","https://openalex.org/W1596364083","https://openalex.org/W1646707810","https://openalex.org/W1771410628","https://openalex.org/W1880549478","https://openalex.org/W1971713783","https://openalex.org/W2012392077","https://openalex.org/W2046513829","https://openalex.org/W2057032881","https://openalex.org/W2118556122","https://openalex.org/W2119717200","https://openalex.org/W2120346334","https://openalex.org/W2130801532","https://openalex.org/W2141007261","https://openalex.org/W2144446635","https://openalex.org/W2145339207","https://openalex.org/W2151416233","https://openalex.org/W2153874061","https://openalex.org/W2155027007","https://openalex.org/W2156974606","https://openalex.org/W2158782408","https://openalex.org/W2162262334","https://openalex.org/W2165150801","https://openalex.org/W2165308133","https://openalex.org/W2167117957","https://openalex.org/W2172968643","https://openalex.org/W2211925278","https://openalex.org/W2253356247","https://openalex.org/W2736601468","https://openalex.org/W2749680651","https://openalex.org/W2890022552","https://openalex.org/W2890192685","https://openalex.org/W2890597452","https://openalex.org/W2898917980","https://openalex.org/W2936304709","https://openalex.org/W2947150733","https://openalex.org/W2949608212","https://openalex.org/W2953334758","https://openalex.org/W2962902376","https://openalex.org/W2963394426","https://openalex.org/W2963704132","https://openalex.org/W2963744705","https://openalex.org/W2963864421","https://openalex.org/W2963960193","https://openalex.org/W2971262355","https://openalex.org/W2991355586","https://openalex.org/W2993185773","https://openalex.org/W3004388863","https://openalex.org/W3016525976","https://openalex.org/W3020882730","https://openalex.org/W3022566517","https://openalex.org/W3025606523","https://openalex.org/W3033324992","https://openalex.org/W3037007430","https://openalex.org/W3037435714","https://openalex.org/W3101192004","https://openalex.org/W3103182070","https://openalex.org/W3116544995","https://openalex.org/W3127984962","https://openalex.org/W3191085025","https://openalex.org/W4213251304","https://openalex.org/W4241811150","https://openalex.org/W4245296547","https://openalex.org/W6632901617","https://openalex.org/W6635607091","https://openalex.org/W6638018090","https://openalex.org/W6639342821","https://openalex.org/W6677737365","https://openalex.org/W6679257226","https://openalex.org/W6681058398","https://openalex.org/W6682074005","https://openalex.org/W6682998330","https://openalex.org/W6683001934","https://openalex.org/W6683204974","https://openalex.org/W6684017535","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6688384279","https://openalex.org/W6691873557","https://openalex.org/W6725941776","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6751494529","https://openalex.org/W6754490743","https://openalex.org/W6754610480","https://openalex.org/W6754627483","https://openalex.org/W6755864697","https://openalex.org/W6757469721","https://openalex.org/W6761682245","https://openalex.org/W6763849353","https://openalex.org/W6771270455","https://openalex.org/W6771428195","https://openalex.org/W6772565584","https://openalex.org/W6776601253","https://openalex.org/W6777091672","https://openalex.org/W6777656069","https://openalex.org/W6779265984","https://openalex.org/W6780559895","https://openalex.org/W6782145165"],"related_works":["https://openalex.org/W3085501055","https://openalex.org/W2988703099","https://openalex.org/W2887443568","https://openalex.org/W2753569380","https://openalex.org/W3210807411","https://openalex.org/W2964068481","https://openalex.org/W2970954742","https://openalex.org/W2979895333","https://openalex.org/W2763287778","https://openalex.org/W3009509472","https://openalex.org/W2950849043","https://openalex.org/W2889893435","https://openalex.org/W3159360018","https://openalex.org/W2444691181","https://openalex.org/W2751325639","https://openalex.org/W3121832314","https://openalex.org/W2145288976","https://openalex.org/W3033120977","https://openalex.org/W3003521509","https://openalex.org/W3010151722"],"abstract_inverted_index":{"Off-policy":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"holds":[4],"the":[5,22,56,94,104,112,120,129,143],"promise":[6],"of":[7,43,58,103,115,123,131,147],"better":[8],"data":[9],"efficiency":[10,149],"as":[11,51],"it":[12,141],"allows":[13],"sample":[14,68,148],"reuse":[15],"and":[16,64,97,119,138],"potentially":[17],"enables":[18],"safe":[19],"interaction":[20],"with":[21],"environment.":[23],"Current":[24],"off-policy":[25],"policy":[26,95,105],"gradient":[27,133],"methods":[28],"either":[29],"suffer":[30],"from":[31],"high":[32,35,67,113,121],"bias":[33,122],"or":[34],"variance,":[36],"delivering":[37],"often":[38],"unreliable":[39],"estimates.":[40],"The":[41,89],"price":[42],"inefficiency":[44],"becomes":[45],"evident":[46],"in":[47,86,145],"real-world":[48],"scenarios":[49],"such":[50],"interaction-driven":[52],"robot":[53],"learning,":[54],"where":[55],"success":[57],"RL":[59],"has":[60],"been":[61],"rather":[62],"limited,":[63],"a":[65,78],"very":[66],"cost":[69],"hinders":[70],"straightforward":[71],"application.":[72],"In":[73,107],"this":[74,108],"paper,":[75],"we":[76,110],"propose":[77],"nonparametric":[79],"Bellman":[80],"equation,":[81],"which":[82],"can":[83],"be":[84],"solved":[85],"closed":[87],"form.":[88],"solution":[90],"is":[91],"differentiable":[92],"w.r.t":[93],"parameters":[96],"gives":[98],"access":[99],"to":[100],"an":[101],"estimation":[102],"gradient.":[106],"way,":[109],"avoid":[111],"variance":[114],"importance":[116],"sampling":[117],"approaches,":[118],"semi-gradient":[124],"methods.":[125],"We":[126],"empirically":[127],"analyze":[128],"quality":[130],"our":[132],"estimate":[134],"against":[135],"state-of-the-art":[136],"methods,":[137],"show":[139],"that":[140],"outperforms":[142],"baselines":[144],"terms":[146],"on":[150],"classical":[151],"control":[152],"tasks.":[153]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}