{"id":"https://openalex.org/W4311354519","doi":"https://doi.org/10.3389/fnbot.2022.1012427","title":"An immediate-return reinforcement learning for the atypical Markov decision processes","display_name":"An immediate-return reinforcement learning for the atypical Markov decision processes","publication_year":2022,"publication_date":"2022-12-13","ids":{"openalex":"https://openalex.org/W4311354519","doi":"https://doi.org/10.3389/fnbot.2022.1012427","pmid":"https://pubmed.ncbi.nlm.nih.gov/36582302"},"language":"en","primary_location":{"id":"doi:10.3389/fnbot.2022.1012427","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2022.1012427","pdf_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2022.1012427/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2022.1012427/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026806553","display_name":"Zebang Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zebang Pan","raw_affiliation_strings":["State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029705981","display_name":"Guilin Wen","orcid":"https://orcid.org/0000-0002-1341-9797"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]},{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guilin Wen","raw_affiliation_strings":["School of Mechanical Engineering, Yanshan University, Qinhuangdao, Hebei, China","State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Yanshan University, Qinhuangdao, Hebei, China","institution_ids":["https://openalex.org/I39333907"]},{"raw_affiliation_string":"State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101028470","display_name":"Zhao Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Tan","raw_affiliation_strings":["State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770656","display_name":"Shan Yin","orcid":"https://orcid.org/0000-0001-9850-3463"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]},{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Yin","raw_affiliation_strings":["School of Mechanical Engineering, Yanshan University, Qinhuangdao, Hebei, China","State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Yanshan University, Qinhuangdao, Hebei, China","institution_ids":["https://openalex.org/I39333907"]},{"raw_affiliation_string":"State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiaoyan Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Hu","raw_affiliation_strings":["State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5029705981"],"corresponding_institution_ids":["https://openalex.org/I16609230","https://openalex.org/I39333907"],"apc_list":{"value":2950,"currency":"USD","value_usd":2950},"apc_paid":{"value":2950,"currency":"USD","value_usd":2950},"fwci":0.4162,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6921258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"16","issue":null,"first_page":"1012427","last_page":"1012427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"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":0.9977999925613403,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9782999753952026,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9718999862670898,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.9030678868293762},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.877556324005127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8757142424583435},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6855225563049316},{"id":"https://openalex.org/keywords/football","display_name":"Football","score":0.5609303712844849},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4910910129547119},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.47024932503700256},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4593513309955597},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43110185861587524},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.37126484513282776}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9030678868293762},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.877556324005127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8757142424583435},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6855225563049316},{"id":"https://openalex.org/C2778444522","wikidata":"https://www.wikidata.org/wiki/Q1081491","display_name":"Football","level":2,"score":0.5609303712844849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4910910129547119},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.47024932503700256},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4593513309955597},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43110185861587524},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.37126484513282776},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fnbot.2022.1012427","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2022.1012427","pdf_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2022.1012427/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},{"id":"pmid:36582302","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36582302","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":"Frontiers in neurorobotics","raw_type":null},{"id":"pmh:oai:doaj.org/article:8f8fcfb6d04845a4b9160dff905444b8","is_oa":true,"landing_page_url":"https://doaj.org/article/8f8fcfb6d04845a4b9160dff905444b8","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Neurorobotics, Vol 16 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9793950","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9793950","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Neurorobot","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3389/fnbot.2022.1012427","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2022.1012427","pdf_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2022.1012427/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2588203316","display_name":null,"funder_award_id":"11832009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4311354519.pdf","grobid_xml":"https://content.openalex.org/works/W4311354519.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1520148289","https://openalex.org/W1932847118","https://openalex.org/W1995986889","https://openalex.org/W2040871222","https://openalex.org/W2052168115","https://openalex.org/W2070827636","https://openalex.org/W2076337359","https://openalex.org/W2133160585","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2165882270","https://openalex.org/W2300655295","https://openalex.org/W2529844623","https://openalex.org/W2559850580","https://openalex.org/W2560192238","https://openalex.org/W2625456521","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2754517384","https://openalex.org/W2762709472","https://openalex.org/W2768233943","https://openalex.org/W2784258528","https://openalex.org/W2787938642","https://openalex.org/W2902143777","https://openalex.org/W2951799221","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W3011120880","https://openalex.org/W3022566517","https://openalex.org/W3082107254","https://openalex.org/W3102274635","https://openalex.org/W3128663285","https://openalex.org/W3164005523","https://openalex.org/W3183630977","https://openalex.org/W4214717370","https://openalex.org/W4225283319","https://openalex.org/W4283394711","https://openalex.org/W4317930919","https://openalex.org/W6683204974","https://openalex.org/W6684921986","https://openalex.org/W6685444567","https://openalex.org/W6692846177","https://openalex.org/W6741002519","https://openalex.org/W6748839928","https://openalex.org/W6756714161","https://openalex.org/W6759126543","https://openalex.org/W6776438516"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2903299703","https://openalex.org/W2156021013","https://openalex.org/W2016648086","https://openalex.org/W4281791088","https://openalex.org/W3105579180","https://openalex.org/W1574958246"],"abstract_inverted_index":{"The":[0],"atypical":[1,27,65,98,122],"Markov":[2],"decision":[3],"processes":[4],"(MDPs)":[5],"are":[6,49,70,127],"decision-making":[7],"for":[8,96],"maximizing":[9],"the":[10,26,35,64,74,78,97,125,131,134,139,147,150,155,170,179],"immediate":[11],"returns":[12],"in":[13,63,176],"only":[14],"one":[15],"state":[16],"transition.":[17],"Many":[18],"complex":[19],"dynamic":[20],"problems":[21],"can":[22],"be":[23],"regarded":[24],"as":[25,161],"MDPs,":[28],"e.g.,":[29],"football":[30,140,148],"trajectory":[31],"control,":[32,183],"approximations":[33],"of":[34,58,77,121,133,182],"compound":[36],"Poincar\u00e9":[37],"maps,":[38],"and":[39,108,113,145,166,184],"parameter":[40],"identification.":[41],"However,":[42],"existing":[43,68,156],"deep":[44,157,162],"reinforcement":[45],"learning":[46,177],"(RL)":[47],"algorithms":[48,69],"designed":[50],"to":[51,82,129,141],"maximize":[52],"long-term":[53],"returns,":[54],"causing":[55],"a":[56,83,114,142],"waste":[57],"computing":[59,185],"resources":[60],"when":[61],"applied":[62],"MDPs.":[66],"These":[67],"also":[71],"limited":[72],"by":[73,104],"estimation":[75],"error":[76],"value":[79],"function,":[80],"leading":[81],"poor":[84],"policy.":[85],"To":[86],"solve":[87],"such":[88,160],"limitations,":[89],"this":[90],"paper":[91],"proposes":[92],"an":[93,106],"immediate-return":[94],"algorithm":[95,172],"MDPs":[99,123],"with":[100,154],"continuous":[101],"action":[102],"space":[103],"designing":[105],"unbiased":[107],"low":[109],"variance":[110],"target":[111],"Q-value":[112],"simplified":[115],"network":[116],"framework.":[117],"Then,":[118],"two":[119],"examples":[120],"considering":[124],"uncertainty":[126],"presented":[128],"illustrate":[130],"performance":[132],"proposed":[135,171],"algorithm,":[136],"i.e.,":[137],"passing":[138],"moving":[143],"player":[144],"chipping":[146],"over":[149],"human":[151],"wall.":[152],"Compared":[153],"RL":[158],"algorithms,":[159],"deterministic":[163],"policy":[164,168],"gradient":[165],"proximal":[167],"optimization,":[169],"shows":[173],"significant":[174],"advantages":[175],"efficiency,":[178],"effective":[180],"rate":[181],"resource":[186],"usage.":[187]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}