{"id":"https://openalex.org/W4205945022","doi":"https://doi.org/10.1109/tnnls.2021.3140042","title":"Self-Punishment and Reward Backfill for Deep <i>Q</i>-Learning","display_name":"Self-Punishment and Reward Backfill for Deep <i>Q</i>-Learning","publication_year":2022,"publication_date":"2022-01-18","ids":{"openalex":"https://openalex.org/W4205945022","doi":"https://doi.org/10.1109/tnnls.2021.3140042"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3140042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3140042","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"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Mohammad Reza Bonyadi","orcid":"https://orcid.org/0000-0003-0061-4902"},"institutions":[{"id":"https://openalex.org/I4210135422","display_name":"Microsoft (Norway)","ror":"https://ror.org/03jtz4s80","country_code":"NO","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210135422"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Mohammad Reza Bonyadi","raw_affiliation_strings":["Microsoft Development Center Norway (MDCN), Trondheim, Norway"],"raw_orcid":"https://orcid.org/0000-0003-0061-4902","affiliations":[{"raw_affiliation_string":"Microsoft Development Center Norway (MDCN), Trondheim, Norway","institution_ids":["https://openalex.org/I4210135422"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1302211766","display_name":"Queensland Health","ror":"https://ror.org/00c1dt378","country_code":"AU","type":"government","lineage":["https://openalex.org/I1302211766","https://openalex.org/I2801244131"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["Turnto Health, Brisbane, QLD, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Turnto Health, Brisbane, QLD, Australia","institution_ids":["https://openalex.org/I1302211766"]}]},{"author_position":"last","author":{"id":null,"display_name":"Maryam Ziaei","orcid":null},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Maryam Ziaei","raw_affiliation_strings":["Kavli Institute for Systems Neuroscience and Jebsen Centre for Alzheimer&#x2019;s Disease, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kavli Institute for Systems Neuroscience and Jebsen Centre for Alzheimer&#x2019;s Disease, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210135422"],"apc_list":null,"apc_paid":null,"fwci":0.9711,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78797999,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"34","issue":"10","first_page":"8086","last_page":"8093"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9384999871253967,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9329000115394592,"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":0.7829999923706055},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6220999956130981},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5468999743461609},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4918000102043152},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.46779999136924744},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4284999966621399}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7829999923706055},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6220999956130981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6219000220298767},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5468999743461609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5202000141143799},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4918000102043152},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.46779999136924744},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4284999966621399},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.30079999566078186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tnnls.2021.3140042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3140042","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W20148665","https://openalex.org/W32403112","https://openalex.org/W2091565802","https://openalex.org/W2145339207","https://openalex.org/W2575705757","https://openalex.org/W2746553466","https://openalex.org/W2788455270","https://openalex.org/W2788862220","https://openalex.org/W2808421695","https://openalex.org/W2963099939","https://openalex.org/W2963523627","https://openalex.org/W3005355833","https://openalex.org/W3041202696","https://openalex.org/W3091628900","https://openalex.org/W6605846256","https://openalex.org/W6638088447","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6740092555","https://openalex.org/W6742461812","https://openalex.org/W6743756900","https://openalex.org/W6754742123","https://openalex.org/W6759301632","https://openalex.org/W6762786500","https://openalex.org/W6770456248"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"agents":[3],"learn":[4],"by":[5,15,66,153,216],"encouraging":[6],"behaviors,":[7],"which":[8],"maximizes":[9],"their":[10,149],"total":[11,150],"reward,":[12],"usually":[13],"provided":[14,25],"the":[16,22,37,54,71,92,107,112,127,135,140,156,190,203,207],"environment.":[17],"In":[18,58],"many":[19],"environments,":[20],"however,":[21],"reward":[23,78,108,151],"is":[24],"after":[26],"a":[27,170],"series":[28],"of":[29,44,126,137,142,148,213],"actions":[30,47,81],"rather":[31],"than":[32],"each":[33],"single":[34],"action,":[35],"leading":[36],"agent":[38,72,93],"to":[39,69,73,99,218],"experience":[40],"ambiguity":[41],"in":[42,139,146,210],"terms":[43,147],"whether":[45],"those":[46],"are":[48],"effective,":[49],"an":[50],"issue":[51],"known":[52],"as":[53],"credit":[55],"assignment":[56],"problem.":[57],"this":[59],"brief,":[60],"we":[61],"propose":[62],"two":[63,115,132,180],"strategies":[64,133,162,181,205],"inspired":[65],"behavioral":[67],"psychology":[68],"enable":[70],"intrinsically":[74],"estimate":[75],"more":[76],"informative":[77],"values":[79],"for":[80],"with":[82,164],"no":[83],"reward.":[84],"The":[85,103],"first":[86],"strategy,":[87,105],"called":[88,106],"self-punishment":[89],"(SP),":[90],"discourages":[91],"from":[94],"making":[95],"mistakes":[96],"that":[97,168,202],"lead":[98],"undesirable":[100],"terminal":[101],"states.":[102],"second":[104],"backfill":[109],"(RB),":[110],"backpropagates":[111],"rewards":[113],"between":[114],"rewarded":[116],"actions.":[117],"We":[118,177],"prove":[119],"that,":[120],"under":[121],"certain":[122],"assumptions":[123],"and":[124,188],"regardless":[125],"RL":[128,166,186],"algorithm":[129,167],"used,":[130],"these":[131,179],"maintain":[134,155],"order":[136],"policies":[138,145],"space":[141],"all":[143],"possible":[144],"and,":[152],"extension,":[154],"optimal":[157],"policy.":[158],"Hence,":[159],"our":[160,199],"proposed":[161,204],"integrate":[163],"any":[165],"learns":[169],"value":[171],"or":[172],"action-value":[173],"function":[174],"through":[175],"experience.":[176],"incorporated":[178],"into":[182],"three":[183],"popular":[184],"deep":[185],"approaches":[187],"evaluated":[189],"results":[191,200],"on":[192],"30":[193],"Atari":[194],"games.":[195],"After":[196],"parameter":[197],"tuning,":[198],"indicate":[201],"improve":[206],"tested":[208,214],"methods":[209],"over":[211,219],"65%":[212],"games":[215],"up":[217],"25":[220],"times":[221],"performance":[222],"improvement.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-01-26T00:00:00"}