{"id":"https://openalex.org/W3168202624","doi":"https://doi.org/10.1109/tnnls.2021.3080521","title":"Orientation-Preserving Rewards\u2019 Balancing in Reinforcement Learning","display_name":"Orientation-Preserving Rewards\u2019 Balancing in Reinforcement Learning","publication_year":2021,"publication_date":"2021-06-11","ids":{"openalex":"https://openalex.org/W3168202624","doi":"https://doi.org/10.1109/tnnls.2021.3080521","mag":"3168202624","pmid":"https://pubmed.ncbi.nlm.nih.gov/34115593"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3080521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3080521","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5044602016","display_name":"Jinsheng Ren","orcid":"https://orcid.org/0000-0002-5013-1880"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinsheng Ren","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","Beijing Innovation Center for Future Chips, Beijing, China","LSBDPA Beijing Key Laboratory, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5013-1880","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing Innovation Center for Future Chips, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"LSBDPA Beijing Key Laboratory, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048321911","display_name":"Shangqi Guo","orcid":"https://orcid.org/0000-0003-3181-6881"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangqi Guo","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","LSBDPA Beijing Key Laboratory, Beijing, China","Beijing Innovation Center for Future Chips, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3181-6881","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"LSBDPA Beijing Key Laboratory, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Beijing Innovation Center for Future Chips, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100352754","display_name":"Feng Chen","orcid":"https://orcid.org/0000-0003-4813-2494"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Chen","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","LSBDPA Beijing Key Laboratory, Beijing, China","Beijing Innovation Center for Future Chips, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4813-2494","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"LSBDPA Beijing Key Laboratory, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Beijing Innovation Center for Future Chips, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0919,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.81291871,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"33","issue":"11","first_page":"6458","last_page":"6472"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9866999983787537,"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"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9847000241279602,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7939109802246094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7151384949684143},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6509809494018555},{"id":"https://openalex.org/keywords/pareto-optimal","display_name":"Pareto optimal","score":0.6408279538154602},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.5299882292747498},{"id":"https://openalex.org/keywords/balance","display_name":"Balance (ability)","score":0.4646316170692444},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4443869888782501},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.43779510259628296},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.4210728406906128},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3157641887664795},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.257360577583313},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17889776825904846},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12473857402801514},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.0928950309753418}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7939109802246094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7151384949684143},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6509809494018555},{"id":"https://openalex.org/C2986314615","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto optimal","level":3,"score":0.6408279538154602},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.5299882292747498},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.4646316170692444},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4443869888782501},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.43779510259628296},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.4210728406906128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3157641887664795},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.257360577583313},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17889776825904846},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12473857402801514},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0928950309753418},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C99508421","wikidata":"https://www.wikidata.org/wiki/Q2678675","display_name":"Physical medicine and rehabilitation","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2021.3080521","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3080521","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:34115593","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34115593","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":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7861851748","display_name":"\u901a\u7528\u7c7b\u8111\u8ba1\u7b97\u67b6\u6784\u6a21\u578b\u4e0e\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61836004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8260862593","display_name":"\u57fa\u4e8e\u6982\u7387\u56fe\u6a21\u578b\u7684\u5927\u89c4\u6a21\u89c6\u89c9\u76ae\u5c42\u8109\u51b2\u795e\u7ecf\u7f51\u7edc\u8ba1\u7b97\u673a\u7406\u7814\u7a76","funder_award_id":"61671266","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":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W47799525","https://openalex.org/W1130790960","https://openalex.org/W1499408472","https://openalex.org/W1543572792","https://openalex.org/W1966630946","https://openalex.org/W1987725948","https://openalex.org/W1999874108","https://openalex.org/W2012612381","https://openalex.org/W2060846151","https://openalex.org/W2064675550","https://openalex.org/W2095564494","https://openalex.org/W2102660061","https://openalex.org/W2111316871","https://openalex.org/W2117428849","https://openalex.org/W2136064843","https://openalex.org/W2141481921","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2151726636","https://openalex.org/W2399852338","https://openalex.org/W2462906003","https://openalex.org/W2522489477","https://openalex.org/W2803767077","https://openalex.org/W2809013025","https://openalex.org/W2962736495","https://openalex.org/W2962937519","https://openalex.org/W2963523627","https://openalex.org/W2963619374","https://openalex.org/W2963864421","https://openalex.org/W2963871073","https://openalex.org/W2964227312","https://openalex.org/W3006334608","https://openalex.org/W4214717370","https://openalex.org/W4293864724","https://openalex.org/W4298857966","https://openalex.org/W6633217410","https://openalex.org/W6637967152","https://openalex.org/W6638088447","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6703271639","https://openalex.org/W6718836005","https://openalex.org/W6729556111","https://openalex.org/W6737327832","https://openalex.org/W6739585900","https://openalex.org/W6740801417","https://openalex.org/W6743660412","https://openalex.org/W6748210908","https://openalex.org/W6749595072","https://openalex.org/W6751869817","https://openalex.org/W6752656891","https://openalex.org/W6756319914","https://openalex.org/W6761908843"],"related_works":["https://openalex.org/W1963790170","https://openalex.org/W2073298047","https://openalex.org/W2033790662","https://openalex.org/W2586328217","https://openalex.org/W2049264236","https://openalex.org/W317165722","https://openalex.org/W2728870795","https://openalex.org/W312725187","https://openalex.org/W1999828099","https://openalex.org/W2078568741"],"abstract_inverted_index":{"Auxiliary":[0],"rewards":[1,20,79,87],"are":[2],"widely":[3],"used":[4],"in":[5,139],"complex":[6],"reinforcement":[7],"learning":[8,125],"tasks.":[9],"However,":[10],"previous":[11],"work":[12],"can":[13,110,152,174],"hardly":[14],"avoid":[15],"the":[16,23,29,32,43,54,67,72,77,81,85,91,95,113,169],"interference":[17],"of":[18,31,56,70],"auxiliary":[19,46],"on":[21],"pursuing":[22],"main":[24,44,78,96,118],"rewards,":[25,155],"which":[26],"leads":[27],"to":[28,41],"destruction":[30],"optimal":[33,64],"policy.":[34],"Thus,":[35],"it":[36,109],"is":[37,88],"challenging":[38],"but":[39],"essential":[40],"balance":[42,154],"and":[45,106,130,135,144,156],"rewards.":[47,119,167],"In":[48,168],"this":[49,99],"article,":[50],"we":[51,101,121],"explicitly":[52],"formulate":[53],"problem":[55],"rewards'":[57,128],"balancing":[58,129],"as":[59],"searching":[60],"for":[61,76,127],"a":[62,103],"Pareto":[63,105],"solution,":[65],"with":[66,90,161,164],"overall":[68],"objective":[69],"preserving":[71],"policy's":[73],"optimization":[74],"orientation":[75],"(i.e.,":[80],"policy":[82,92,114],"driven":[83,93],"by":[84,94],"balanced":[86],"consistent":[89],"rewards).":[97],"To":[98],"end,":[100],"propose":[102],"variant":[104],"show":[107],"that":[108,149],"effectively":[111,153],"guide":[112],"search":[115],"toward":[116],"more":[117],"Furthermore,":[120],"establish":[122],"an":[123],"iterative":[124],"framework":[126],"theoretically":[131],"analyze":[132],"its":[133],"convergence":[134],"time":[136],"complexity.":[137],"Experiments":[138],"both":[140],"discrete":[141],"(grid":[142],"word)":[143],"continuous":[145],"(Doom)":[146],"environments":[147],"demonstrated":[148],"our":[150,172],"algorithm":[151,173],"achieve":[157],"remarkable":[158],"performance":[159],"compared":[160],"those":[162],"RLs":[163],"heuristically":[165],"designed":[166],"ViZDoom":[170],"platform,":[171],"learn":[175],"expert-level":[176],"policies.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}