{"id":"https://openalex.org/W3198568807","doi":"https://doi.org/10.1109/isit45174.2021.9518023","title":"Actor-only Deterministic Policy Gradient via Zeroth-order Gradient Oracles in Action Space","display_name":"Actor-only Deterministic Policy Gradient via Zeroth-order Gradient Oracles in Action Space","publication_year":2021,"publication_date":"2021-07-12","ids":{"openalex":"https://openalex.org/W3198568807","doi":"https://doi.org/10.1109/isit45174.2021.9518023","mag":"3198568807"},"language":"en","primary_location":{"id":"doi:10.1109/isit45174.2021.9518023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit45174.2021.9518023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055323351","display_name":"Harshat Kumar","orcid":"https://orcid.org/0000-0001-7520-2799"},"institutions":[{"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":true,"raw_author_name":"Harshat Kumar","raw_affiliation_strings":["University of Pennsylvania,Department of Electrical and Systems Engineering,Philadelphia,PA,USA,19104","Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania,Department of Electrical and Systems Engineering,Philadelphia,PA,USA,19104","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091493591","display_name":"Dionysios S. Kalogerias","orcid":null},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dionysios S. Kalogerias","raw_affiliation_strings":["Michigan State University,Department of Electrical and Computer Engineering,East Lansing,MI,USA,48824","Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USA"],"affiliations":[{"raw_affiliation_string":"Michigan State University,Department of Electrical and Computer Engineering,East Lansing,MI,USA,48824","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029243115","display_name":"George J. Pappas","orcid":"https://orcid.org/0000-0001-9081-0637"},"institutions":[{"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":"George J. Pappas","raw_affiliation_strings":["University of Pennsylvania,Department of Electrical and Systems Engineering,Philadelphia,PA,USA,19104","Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania,Department of Electrical and Systems Engineering,Philadelphia,PA,USA,19104","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078862959","display_name":"Alejandro Ribeiro","orcid":"https://orcid.org/0000-0003-4230-9906"},"institutions":[{"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":"Alejandro Ribeiro","raw_affiliation_strings":["University of Pennsylvania,Department of Electrical and Systems Engineering,Philadelphia,PA,USA,19104","Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania,Department of Electrical and Systems Engineering,Philadelphia,PA,USA,19104","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055323351"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.12864122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1676","last_page":"1681"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9980000257492065,"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/T12288","display_name":"Optimization and Search Problems","score":0.9977999925613403,"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/randomness","display_name":"Randomness","score":0.618553876876831},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.559960126876831},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5040242075920105},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4865802526473999},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4491429924964905},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4422123432159424},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4358736276626587},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35520854592323303},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34722059965133667},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3032282590866089},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16264238953590393},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11556699872016907}],"concepts":[{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.618553876876831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.559960126876831},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5040242075920105},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4865802526473999},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4491429924964905},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4422123432159424},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4358736276626587},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35520854592323303},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34722059965133667},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3032282590866089},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16264238953590393},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11556699872016907},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit45174.2021.9518023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit45174.2021.9518023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W1777239053","https://openalex.org/W1977655452","https://openalex.org/W2070315235","https://openalex.org/W2108682071","https://openalex.org/W2149479912","https://openalex.org/W2155027007","https://openalex.org/W2165150801","https://openalex.org/W2171830216","https://openalex.org/W2173248099","https://openalex.org/W2575705757","https://openalex.org/W2611484353","https://openalex.org/W2696558042","https://openalex.org/W2771144749","https://openalex.org/W2787938642","https://openalex.org/W2883094398","https://openalex.org/W2886474253","https://openalex.org/W2896844199","https://openalex.org/W2912541037","https://openalex.org/W2951915386","https://openalex.org/W2963864421","https://openalex.org/W2981237928","https://openalex.org/W2983476703","https://openalex.org/W2996611387","https://openalex.org/W2998481680","https://openalex.org/W3034675169","https://openalex.org/W3092621452","https://openalex.org/W3109546547","https://openalex.org/W3136903997","https://openalex.org/W4287758272","https://openalex.org/W4287979710","https://openalex.org/W4287991904","https://openalex.org/W4288614813","https://openalex.org/W4289743128","https://openalex.org/W4302570325","https://openalex.org/W4318718437","https://openalex.org/W6638018090","https://openalex.org/W6638088447","https://openalex.org/W6676023451","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6748839928","https://openalex.org/W6752877344","https://openalex.org/W6754297394","https://openalex.org/W6758646351","https://openalex.org/W6764419582","https://openalex.org/W6769467134","https://openalex.org/W6769623760","https://openalex.org/W6772013758","https://openalex.org/W6772677550","https://openalex.org/W6779874797"],"related_works":["https://openalex.org/W3034924094","https://openalex.org/W3094954546","https://openalex.org/W1488708774","https://openalex.org/W2981906196","https://openalex.org/W4391100477","https://openalex.org/W4327779705","https://openalex.org/W1513698804","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"Deterministic":[0],"policies":[1],"demonstrate":[2],"substantial":[3],"empirical":[4],"success":[5],"over":[6],"their":[7],"stochastic":[8,25,68],"counterparts":[9],"as":[10,49,170],"they":[11],"remove":[12],"a":[13,75,104,167],"level":[14],"of":[15,38,54,66,74,86,132,136,145,149,162],"randomness":[16],"in":[17,134,147,166],"Policy":[18],"Gradient":[19],"(PG)":[20],"methods":[21],"when":[22],"applied":[23],"to":[24,51,70,129,142],"search":[26],"problems":[27],"involving":[28],"Markov":[29],"decision":[30],"processes.":[31],"However,":[32],"current":[33],"implementations":[34],"require":[35],"the":[36,55,64,87,101,160],"use":[37,65],"state-action":[39],"value":[40],"(":[41],"<tex":[42,77,88],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[43,78,89],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$Q$</tex>":[44,79,90],"-function)":[45],"approximators,":[46],"also":[47],"known":[48],"critics,":[50],"obtain":[52,71],"estimates":[53,73],"associated":[56],"policy-reward":[57],"gradient.":[58],"In":[59,117],"this":[60],"work,":[61],"we":[62],"propose":[63],"two-point":[67],"evaluations":[69],"gradient":[72],"smoothed":[76],"-function":[80,91],"surrogate,":[81],"constructed":[82],"by":[83,127,140],"evaluating":[84],"pairs":[85],"at":[92],"low-dimensional,":[93],"randomized":[94],"initial":[95],"action":[96],"perturbations.":[97],"This":[98],"procedure":[99],"lifts":[100],"dependence":[102],"on":[103,154],"critic":[105],"and":[106,112,139],"restores":[107],"true":[108],"model-free":[109],"policy":[110],"learning,":[111],"with":[113],"provable":[114],"algorithmic":[115],"stability.":[116],"fact,":[118],"our":[119,163],"finite":[120],"complexity":[121],"bounds":[122],"improve":[123],"upon":[124],"existing":[125],"results":[126,153],"up":[128,141],"2":[130],"orders":[131,144],"magnitude":[133,146],"terms":[135,148],"iteration":[137],"complexity,":[138],"3/2":[143],"sample":[150],"complexity.":[151],"Simulation":[152],"an":[155],"agent":[156],"navigation":[157],"problem":[158],"showcase":[159],"effectiveness":[161],"proposed":[164],"algorithm":[165],"practical":[168],"setting,":[169],"well.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}