{"id":"https://openalex.org/W3207294509","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892303","title":"Neural Network Compatible Off-Policy Natural Actor-Critic Algorithm","display_name":"Neural Network Compatible Off-Policy Natural Actor-Critic Algorithm","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W3207294509","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892303","mag":"3207294509"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892303","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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/A5002033038","display_name":"Raghuram Bharadwaj Diddigi","orcid":"https://orcid.org/0000-0003-0233-0698"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Raghuram Bharadwaj Diddigi","raw_affiliation_strings":["Indian Institute of Science,Department of Computer Science and Automation,Bengaluru,India","Department of Computer Science and Automation, Indian Institute of Science, Bengaluru, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Department of Computer Science and Automation,Bengaluru,India","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Department of Computer Science and Automation, Indian Institute of Science, Bengaluru, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101633144","display_name":"Prateek Jain","orcid":"https://orcid.org/0000-0002-9233-5160"},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prateek Jain","raw_affiliation_strings":["Indian Institute of Technology,Department of Computer Science and Engineering,Dharwad,India","Department of Computer Science and Engineering, Indian Institute of Technology, Dharwad, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Department of Computer Science and Engineering,Dharwad,India","institution_ids":["https://openalex.org/I4210152718"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology, Dharwad, India","institution_ids":["https://openalex.org/I4210152718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006298931","display_name":"Prabuchandran K. J","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prabuchandran K. J","raw_affiliation_strings":["Indian Institute of Technology,Department of Computer Science and Engineering,Dharwad,India","Department of Computer Science and Engineering, Indian Institute of Technology, Dharwad, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Department of Computer Science and Engineering,Dharwad,India","institution_ids":["https://openalex.org/I4210152718"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology, Dharwad, India","institution_ids":["https://openalex.org/I4210152718"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038163398","display_name":"Shalabh Bhatnagar","orcid":"https://orcid.org/0000-0001-7644-3914"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shalabh Bhatnagar","raw_affiliation_strings":["Indian Institute of Science,Department of Computer Science and Automation,Bengaluru,India","Department of Computer Science and Automation, Indian Institute of Science, Bengaluru, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Department of Computer Science and Automation,Bengaluru,India","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Department of Computer Science and Automation, Indian Institute of Science, Bengaluru, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002033038"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.2087,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.37117117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"99","issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9839000105857849,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.955299973487854,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6319419145584106},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5758253931999207},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5580003261566162},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34189486503601074},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3243827223777771},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.10819333791732788}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6319419145584106},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5758253931999207},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5580003261566162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34189486503601074},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3243827223777771},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.10819333791732788},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892303","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai::77925","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1631749026","display_name":null,"funder_award_id":"Fellowship","funder_id":"https://openalex.org/F4320310071","funder_display_name":"Indian Institute of Science"},{"id":"https://openalex.org/G4018744250","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320320719","funder_display_name":"Department of Science and Technology, Ministry of Science and Technology, India"},{"id":"https://openalex.org/G4412498071","display_name":null,"funder_award_id":"India","funder_id":"https://openalex.org/F4320320719","funder_display_name":"Department of Science and Technology, Ministry of Science and Technology, India"},{"id":"https://openalex.org/G6057166352","display_name":null,"funder_award_id":"SRG/2021/000048","funder_id":"https://openalex.org/F4320334771","funder_display_name":"Science and Engineering Research Board"},{"id":"https://openalex.org/G6771488830","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320334771","funder_display_name":"Science and Engineering Research Board"},{"id":"https://openalex.org/G7800732931","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320334771","funder_display_name":"Science and Engineering Research Board"},{"id":"https://openalex.org/G8754380281","display_name":null,"funder_award_id":"fellowship","funder_id":"https://openalex.org/F4320334771","funder_display_name":"Science and Engineering Research Board"}],"funders":[{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320310071","display_name":"Indian Institute of Science","ror":"https://ror.org/04dese585"},{"id":"https://openalex.org/F4320320691","display_name":"Department of Science and Technology, Republic of South Africa","ror":"https://ror.org/048kh7197"},{"id":"https://openalex.org/F4320320719","display_name":"Department of Science and Technology, Ministry of Science and Technology, India","ror":"https://ror.org/0101xrq71"},{"id":"https://openalex.org/F4320334035","display_name":"Robert Bosch Centre for Cyber-Physical Systems, Indian Institute of Science Bangalore","ror":null},{"id":"https://openalex.org/F4320334771","display_name":"Science and Engineering Research Board","ror":"https://ror.org/03ffdsr55"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W594357522","https://openalex.org/W1515851193","https://openalex.org/W1547925194","https://openalex.org/W1594783240","https://openalex.org/W1614417283","https://openalex.org/W1771410628","https://openalex.org/W1970789124","https://openalex.org/W1991119064","https://openalex.org/W2027648864","https://openalex.org/W2075268401","https://openalex.org/W2094387729","https://openalex.org/W2130801532","https://openalex.org/W2134042548","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2172968643","https://openalex.org/W2235056388","https://openalex.org/W2256989395","https://openalex.org/W2475651303","https://openalex.org/W2556958149","https://openalex.org/W2749928749","https://openalex.org/W2781726626","https://openalex.org/W2802314255","https://openalex.org/W2890047470","https://openalex.org/W2897394476","https://openalex.org/W2904789544","https://openalex.org/W2923913124","https://openalex.org/W2945554113","https://openalex.org/W2949608212","https://openalex.org/W2951470703","https://openalex.org/W2953334758","https://openalex.org/W2953722837","https://openalex.org/W2962902376","https://openalex.org/W2963095800","https://openalex.org/W2964043796","https://openalex.org/W2964543613","https://openalex.org/W3035361730","https://openalex.org/W3129673291","https://openalex.org/W3131821770","https://openalex.org/W3167990336","https://openalex.org/W4243772471","https://openalex.org/W4288405579","https://openalex.org/W4307347247","https://openalex.org/W6632901617","https://openalex.org/W6635508374","https://openalex.org/W6638018090","https://openalex.org/W6679257226","https://openalex.org/W6683001934","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W6692846177","https://openalex.org/W6730111887","https://openalex.org/W6743802245","https://openalex.org/W6747473740","https://openalex.org/W6754627483","https://openalex.org/W6760862771","https://openalex.org/W6762441359","https://openalex.org/W6779651760","https://openalex.org/W6790690321","https://openalex.org/W6791107212","https://openalex.org/W7065010408"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Learning":[0,15],"optimal":[1,33,51,62,176],"behavior":[2,47,59,63,105],"from":[3,40,57,79],"existing":[4,115],"data":[5,38,78],"is":[6,18,29,64,83],"one":[7,155],"of":[8,182],"the":[9,37,41,46,50,58,68,73,80,103,107,144,163,166,180,183,193],"most":[10],"important":[11],"problems":[12],"in":[13,23,67,86,139],"Reinforcement":[14],"(RL).":[16],"This":[17,88,133],"known":[19],"as":[20,45],"\u201coff-policy":[21],"control\u201d":[22],"RL":[24,141,200],"where":[25,76],"an":[26,32,91],"agent's":[27],"objective":[28],"to":[30,72,136,156,161,173],"compute":[31],"policy":[34,43,52,81,109,129,164],"based":[35],"on":[36,198],"obtained":[39],"given":[42],"(known":[44],"policy).":[48],"As":[49],"can":[53],"be":[54],"very":[55,65],"different":[56],"policy,":[60],"learning":[61,138],"hard":[66],"\u201coff-policy\u201d":[69],"setting":[70,75],"compared":[71],"\u201con-policy\u201d":[74],"new":[77],"updates":[82],"typically":[84],"utilized":[85],"learning.":[87],"work":[89],"proposes":[90],"off-policy":[92,104,185],"natural":[93,108,116,186],"actor-critic":[94,118,196],"algorithm":[95,149,188,197],"that":[96,153],"utilizes":[97,150],"state-action":[98],"distribution":[99],"correction":[100],"for":[101,111,126],"handling":[102],"and":[106,130,165,169],"gradient":[110,187,195],"sample":[112],"efficiency.":[113],"The":[114],"gradient-based":[117],"algorithms":[119],"with":[120,192],"convergence":[121,172],"guarantees":[122],"require":[123],"fixed":[124],"features":[125,152],"approximating":[127],"both":[128],"value":[131,167],"functions.":[132],"often":[134],"leads":[135],"sub-optimal":[137],"many":[140],"applications.":[142],"On":[143],"other":[145],"hand,":[146],"our":[147],"proposed":[148,184],"compatible":[151],"enable":[154],"use":[157],"arbitrary":[158],"neural":[159],"networks":[160],"approximate":[162],"function":[168],"yet":[170],"guarantee":[171],"a":[174],"locally":[175],"policy.":[177],"We":[178],"illustrate":[179],"benefit":[181],"by":[189],"comparing":[190],"it":[191],"vanilla":[194],"benchmark":[199],"tasks.":[201]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}