{"id":"https://openalex.org/W2969428710","doi":"https://doi.org/10.1109/access.2019.2936863","title":"Rewards Prediction-Based Credit Assignment for Reinforcement Learning With Sparse Binary Rewards","display_name":"Rewards Prediction-Based Credit Assignment for Reinforcement Learning With Sparse Binary Rewards","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2969428710","doi":"https://doi.org/10.1109/access.2019.2936863","mag":"2969428710"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2936863","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2936863","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08809762.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08809762.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052308329","display_name":"Minah Seo","orcid":"https://orcid.org/0000-0003-0841-5190"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minah Seo","raw_affiliation_strings":["The Cho Chun Shik Graduate School of Green Transportation, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-0841-5190","affiliations":[{"raw_affiliation_string":"The Cho Chun Shik Graduate School of Green Transportation, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057428816","display_name":"Luiz Felipe Vecchietti","orcid":"https://orcid.org/0000-0003-2862-6200"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Luiz Felipe Vecchietti","raw_affiliation_strings":["The Cho Chun Shik Graduate School of Green Transportation, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Cho Chun Shik Graduate School of Green Transportation, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037786080","display_name":"Sangkeum Lee","orcid":"https://orcid.org/0000-0001-6918-124X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangkeum Lee","raw_affiliation_strings":["The Cho Chun Shik Graduate School of Green Transportation, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-6918-124X","affiliations":[{"raw_affiliation_string":"The Cho Chun Shik Graduate School of Green Transportation, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005393869","display_name":"Dongsoo Har","orcid":"https://orcid.org/0000-0002-6949-1739"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongsoo Har","raw_affiliation_strings":["The Cho Chun Shik Graduate School of Green Transportation, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-6949-1739","affiliations":[{"raw_affiliation_string":"The Cho Chun Shik Graduate School of Green Transportation, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":3.1062,"has_fulltext":true,"cited_by_count":49,"citation_normalized_percentile":{"value":0.93393157,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"7","issue":null,"first_page":"118776","last_page":"118791"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.9531999826431274,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9372000098228455,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7783036231994629},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7688689231872559},{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.7129536867141724},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6888693571090698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6697104573249817},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6583349108695984},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.603643000125885},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.569024920463562},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.4407755434513092},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42875465750694275},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4189993739128113},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09793660044670105},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.09263604879379272},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.08070874214172363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7783036231994629},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7688689231872559},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.7129536867141724},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6888693571090698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6697104573249817},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6583349108695984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.603643000125885},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.569024920463562},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4407755434513092},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42875465750694275},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4189993739128113},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09793660044670105},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.09263604879379272},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.08070874214172363},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2936863","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2936863","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08809762.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1b387611946a44e397715056f90c7a7e","is_oa":true,"landing_page_url":"https://doaj.org/article/1b387611946a44e397715056f90c7a7e","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":"IEEE Access, Vol 7, Pp 118776-118791 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2936863","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2936863","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08809762.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G6325122985","display_name":null,"funder_award_id":"2018-0-00677","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8025487768","display_name":null,"funder_award_id":"2018-0-00677","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2969428710.pdf","grobid_xml":"https://content.openalex.org/works/W2969428710.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1522301498","https://openalex.org/W1569296262","https://openalex.org/W1617610651","https://openalex.org/W1769460679","https://openalex.org/W1796544916","https://openalex.org/W1934909785","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2158969944","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2553109721","https://openalex.org/W2583993537","https://openalex.org/W2605368761","https://openalex.org/W2624731731","https://openalex.org/W2772709170","https://openalex.org/W2788455270","https://openalex.org/W2789008106","https://openalex.org/W2899026301","https://openalex.org/W2909711564","https://openalex.org/W2949600457","https://openalex.org/W2950892788","https://openalex.org/W2962948087","https://openalex.org/W2963099939","https://openalex.org/W2963477884","https://openalex.org/W2963864421","https://openalex.org/W2964001908","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W2966477667","https://openalex.org/W3100944043","https://openalex.org/W4293872189","https://openalex.org/W4300799055","https://openalex.org/W6631190155","https://openalex.org/W6634103402","https://openalex.org/W6636433691","https://openalex.org/W6637770816","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6730013898","https://openalex.org/W6736469832","https://openalex.org/W6740801417","https://openalex.org/W6746177919","https://openalex.org/W6747861887","https://openalex.org/W6748599296","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3197854638","https://openalex.org/W3140454661","https://openalex.org/W4245029315","https://openalex.org/W2139970489","https://openalex.org/W1492315459","https://openalex.org/W1512434910","https://openalex.org/W2540910169","https://openalex.org/W3089780453","https://openalex.org/W3148904318","https://openalex.org/W3012552522"],"abstract_inverted_index":{"In":[0,178],"reinforcement":[1,5],"learning":[2],"(RL),":[3],"a":[4,68,76,82,108,205,230],"signal":[6],"may":[7],"be":[8],"infrequent":[9],"and":[10,88,128,142,190,197],"delayed,":[11],"not":[12],"appearing":[13],"immediately":[14],"after":[15,59],"the":[16,20,40,63,97,103,118,126,172,179,192,201,225,228],"action":[17,100],"that":[18,112,184,209],"triggered":[19],"reward.":[21],"To":[22,65],"trace":[23],"back":[24],"what":[25],"sequence":[26,77],"of":[27,39,62,72,78,157,207],"actions":[28,79],"contributes":[29],"to":[30,80,102,125,215,237],"delayed":[31],"rewards,":[32,52,87],"e.g.,":[33],"credit":[34],"assignment":[35],"(CA),":[36],"is":[37,47,91,105,162,182,210,219,240],"one":[38],"biggest":[41],"challenges":[42],"in":[43,171,200,224],"RL.":[44],"This":[45],"challenge":[46],"aggravated":[48],"under":[49,84],"sparse":[50,85],"binary":[51,86],"especially":[53],"when":[54],"rewards":[55,115,122],"are":[56,123,153],"given":[57],"only":[58],"successful":[60],"completion":[61],"task.":[64],"this":[66],"end,":[67],"novel":[69],"method":[70,161,186],"consisting":[71],"key-action":[73,94,127],"detection,":[74],"among":[75],"perform":[81],"task":[83,208],"CA":[89,151,234],"strategy":[90,235],"proposed.":[92],"The":[93,121],"defined":[95,132],"as":[96,133,155,213],"most":[98],"important":[99],"contributing":[101],"reward":[104],"detected":[106],"by":[107,221],"deep":[109],"neural":[110],"network":[111],"predicts":[113],"future":[114],"based":[116],"on":[117],"environment":[119],"information.":[120],"re-assigned":[124],"its":[129],"adjacent":[130],"actions,":[131],"adjacent-key-actions.":[134],"Such":[135],"re-assignment":[136],"process":[137],"enables":[138],"increased":[139],"success":[140,195],"rate":[141,196],"convergence":[143,198],"speed":[144],"during":[145],"training.":[146],"For":[147],"efficient":[148],"re-assignment,":[149],"two":[150],"strategies":[152],"considered":[154],"part":[156],"proposed":[158,185],"method.":[159],"Proposed":[160],"combined":[163],"with":[164,246],"hindsight":[165],"experience":[166],"replay":[167],"(HER)":[168],"for":[169,232],"experiments":[170],"OpenAI":[173],"gym":[174],"suite":[175],"robotics":[176],"environment.":[177],"experiments,":[180,229],"it":[181],"demonstrated":[183],"can":[187],"detect":[188],"key-actions":[189],"outperform":[191],"HER,":[193],"increasing":[194],"speed,":[199],"Fetch":[202],"slide":[203],"task,":[204],"type":[206],"more":[211],"exacting":[212],"compared":[214],"other":[216],"tasks,":[217],"but":[218],"addressed":[220],"few":[222],"publications":[223],"literature.":[226],"From":[227],"guideline":[231],"selecting":[233],"according":[236],"goal":[238,243],"location":[239],"provided":[241],"through":[242],"distribution":[244],"analysis":[245],"dot":[247],"map.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":6}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}