{"id":"https://openalex.org/W3046641743","doi":"https://doi.org/10.1109/iros45743.2020.9341559","title":"Proximal Deterministic Policy Gradient","display_name":"Proximal Deterministic Policy Gradient","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3046641743","doi":"https://doi.org/10.1109/iros45743.2020.9341559","mag":"3046641743"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9341559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.00759","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006010436","display_name":"Marco Maggipinto","orcid":"https://orcid.org/0000-0003-4705-9651"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Maggipinto","raw_affiliation_strings":["Department of Information Engineering, University of Padova, Padova, Italy","University of Padova, Department of Information Engineering, Padova, ITALY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, University of Padova, Padova, Italy","institution_ids":["https://openalex.org/I138689650"]},{"raw_affiliation_string":"University of Padova, Department of Information Engineering, Padova, ITALY","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026617079","display_name":"Gian Antonio Susto","orcid":"https://orcid.org/0000-0001-5739-9639"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gian Antonio Susto","raw_affiliation_strings":["Department of Information Engineering, University of Padova, Padova, Italy",">University of Padua"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, University of Padova, Padova, Italy","institution_ids":["https://openalex.org/I138689650"]},{"raw_affiliation_string":">University of Padua","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006038667","display_name":"Pratik Chaudhari","orcid":"https://orcid.org/0000-0003-4590-1956"},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pratik Chaudhari","raw_affiliation_strings":["Electrical and Systems Engineering Department, University of Pennsylvania, Philadelphia, PA, USA","#N#               * University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Systems Engineering Department, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":["https://openalex.org/I36788626","https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"5438","last_page":"5444"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10603","display_name":"Smart Grid Energy Management","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8360002040863037},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6928583383560181},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.6759566068649292},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5175168514251709},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.500108003616333},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4927103817462921},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.48072126507759094},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.43829184770584106},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4308319687843323},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4256054759025574},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3936772644519806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32915520668029785},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21504759788513184},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19349345564842224}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8360002040863037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6928583383560181},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.6759566068649292},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5175168514251709},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.500108003616333},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4927103817462921},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.48072126507759094},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.43829184770584106},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4308319687843323},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4256054759025574},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3936772644519806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32915520668029785},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21504759788513184},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19349345564842224},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/iros45743.2020.9341559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.00759","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.00759","pdf_url":"https://arxiv.org/pdf/2008.00759","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":"","raw_type":null},{"id":"mag:3046641743","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2008.00759","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":"pmh:oai:www.research.unipd.it:11577/3371785","is_oa":false,"landing_page_url":"http://hdl.handle.net/11577/3371785","pdf_url":null,"source":{"id":"https://openalex.org/S4306402547","display_name":"Padua Research Archive (University of Padova)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"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":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2008.00759","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.00759","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.00759","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.00759","pdf_url":"https://arxiv.org/pdf/2008.00759","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":"","raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3046641743.pdf","grobid_xml":"https://content.openalex.org/works/W3046641743.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W51508254","https://openalex.org/W1191599655","https://openalex.org/W1522301498","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W2121863487","https://openalex.org/W2155027007","https://openalex.org/W2155968351","https://openalex.org/W2156387975","https://openalex.org/W2156737235","https://openalex.org/W2158782408","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2913535645","https://openalex.org/W2945624305","https://openalex.org/W2949996623","https://openalex.org/W2963480765","https://openalex.org/W2964043796","https://openalex.org/W2965920802","https://openalex.org/W4244393449","https://openalex.org/W6602057636","https://openalex.org/W6627932998","https://openalex.org/W6631190155","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6682889407","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6752164047","https://openalex.org/W6756061209","https://openalex.org/W6762263229","https://openalex.org/W6762719077","https://openalex.org/W6780559895","https://openalex.org/W7014788697"],"related_works":["https://openalex.org/W3130181846","https://openalex.org/W1996919881","https://openalex.org/W2988737553","https://openalex.org/W3131320809","https://openalex.org/W3094567409","https://openalex.org/W2975587412","https://openalex.org/W2184469785","https://openalex.org/W3046114900","https://openalex.org/W3008654577","https://openalex.org/W2398624391","https://openalex.org/W2809329936","https://openalex.org/W3130610232","https://openalex.org/W2907303449","https://openalex.org/W2963630259","https://openalex.org/W2510228645","https://openalex.org/W1521795138","https://openalex.org/W3186722754","https://openalex.org/W2967312566","https://openalex.org/W2769602321","https://openalex.org/W2198341036"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"two":[3,47],"simple":[4],"techniques":[5],"to":[6,56],"improve":[7],"off-policy":[8,16,54],"Reinforcement":[9],"Learning":[10],"(RL)":[11],"algorithms.":[12],"First,":[13],"we":[14,44,72],"formulate":[15],"RL":[17,83],"as":[18],"a":[19],"stochastic":[20],"proximal":[21,41],"point":[22],"iteration.":[23],"The":[24],"target":[25],"network":[26,38],"plays":[27],"the":[28,31,36,40,46],"role":[29],"of":[30,33,68],"variable":[32],"optimization":[34],"and":[35],"value":[37,48,61],"computes":[39],"operator.":[42],"Second,":[43],"exploits":[45],"functions":[49],"commonly":[50],"employed":[51],"in":[52],"state-of-the-art":[53,78],"algorithms":[55,79],"provide":[57],"an":[58],"improved":[59],"action":[60],"estimate":[62],"through":[63],"bootstrapping":[64],"with":[65],"limited":[66],"increase":[67],"computational":[69],"resources.":[70],"Further,":[71],"demonstrate":[73],"significant":[74],"performance":[75],"improvement":[76],"over":[77],"on":[80],"standard":[81],"continuous-control":[82],"benchmarks.":[84]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}