{"id":"https://openalex.org/W3205784920","doi":"https://doi.org/10.1609/aaai.v36i8.20874","title":"Hindsight Network Credit Assignment: Efficient Credit Assignment in Networks of Discrete Stochastic Units","display_name":"Hindsight Network Credit Assignment: Efficient Credit Assignment in Networks of Discrete Stochastic Units","publication_year":2022,"publication_date":"2022-06-28","ids":{"openalex":"https://openalex.org/W3205784920","doi":"https://doi.org/10.1609/aaai.v36i8.20874","mag":"3205784920"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v36i8.20874","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v36i8.20874","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/20874/20633","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/20874/20633","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007831673","display_name":"Kenny Young","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Kenny Young","raw_affiliation_strings":["University of Alberta"],"affiliations":[{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5007831673"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":0.1039,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.22128852,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"36","issue":"8","first_page":"8919","last_page":"8926"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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/T11612","display_name":"Stochastic Gradient Optimization Techniques","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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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/backpropagation","display_name":"Backpropagation","score":0.6315301656723022},{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.6304482817649841},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6169511675834656},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5342490077018738},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5084999799728394},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4768282473087311},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4293183982372284},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4268348217010498},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37347519397735596},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34698694944381714},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.11457127332687378},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09724056720733643}],"concepts":[{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.6315301656723022},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.6304482817649841},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6169511675834656},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5342490077018738},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5084999799728394},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4768282473087311},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4293183982372284},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4268348217010498},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37347519397735596},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34698694944381714},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11457127332687378},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09724056720733643},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v36i8.20874","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v36i8.20874","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/20874/20633","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v36i8.20874","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v36i8.20874","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/20874/20633","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320325651","display_name":"Alberta Innovates","ror":null},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3205784920.pdf","grobid_xml":"https://content.openalex.org/works/W3205784920.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W2119717200","https://openalex.org/W2122262818","https://openalex.org/W2135354436","https://openalex.org/W2159080219","https://openalex.org/W2186389117","https://openalex.org/W2187669537","https://openalex.org/W2242818861","https://openalex.org/W2259167532","https://openalex.org/W2547875792","https://openalex.org/W2548228487","https://openalex.org/W2602076750","https://openalex.org/W2767002724","https://openalex.org/W2909637611","https://openalex.org/W2952264928","https://openalex.org/W2962897886","https://openalex.org/W2963351648","https://openalex.org/W2963675378","https://openalex.org/W2963851840","https://openalex.org/W2964121744","https://openalex.org/W2966628687","https://openalex.org/W2972821612","https://openalex.org/W3034756459","https://openalex.org/W3036990844","https://openalex.org/W3099014706","https://openalex.org/W3122690883","https://openalex.org/W3129576130","https://openalex.org/W3136591341","https://openalex.org/W4230563027","https://openalex.org/W4287998216","https://openalex.org/W4293415974","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6686467684","https://openalex.org/W6695087160","https://openalex.org/W6729448088","https://openalex.org/W6779423468","https://openalex.org/W6783988234"],"related_works":["https://openalex.org/W3197854638","https://openalex.org/W2894173309","https://openalex.org/W4387932263","https://openalex.org/W2157746493","https://openalex.org/W2371065793","https://openalex.org/W1977222966","https://openalex.org/W3122602933","https://openalex.org/W2950038056","https://openalex.org/W1544940847","https://openalex.org/W2289285490"],"abstract_inverted_index":{"Training":[0],"neural":[1],"networks":[2,23,45],"with":[3,24,81],"discrete":[4,47,185],"stochastic":[5,26,48,165,217],"variables":[6],"presents":[7],"a":[8,39,104,110,154,162,184],"unique":[9],"challenge.":[10],"Backpropagation":[11],"is":[12,93,114,140,170],"not":[13],"directly":[14],"applicable,":[15],"nor":[16],"are":[17],"the":[18,60,71,86,90,117,132,159,168,173,201],"reparameterization":[19],"tricks":[20],"used":[21],"in":[22,70,103,216],"continuous":[25],"variables.":[27],"To":[28],"address":[29],"this":[30,120,177],"challenge,":[31],"we":[32,122],"present":[33],"Hindsight":[34],"Network":[35],"Credit":[36],"Assignment":[37],"(HNCA),":[38],"novel":[40],"gradient":[41,79],"estimation":[42],"algorithm":[43],"for":[44],"of":[46,97,158,161,164,180,210],"units.":[49],"HNCA":[50,76,102,126,148,181,204],"works":[51],"by":[52,136],"assigning":[53],"credit":[54,214],"to":[55,62,85,95,108,116,152,172,182,194],"each":[56],"unit":[57],"based":[58],"on":[59],"degree":[61],"which":[63],"its":[64,67],"output":[65],"influences":[66],"immediate":[68],"children":[69],"network.":[72],"We":[73,99,144,175,198],"prove":[74],"that":[75,96,113,125,131,200],"produces":[77],"unbiased":[78],"estimates":[80],"reduced":[82],"variance":[83,133],"compared":[84],"REINFORCE":[87],"estimator,":[88],"while":[89],"computational":[91],"cost":[92],"similar":[94],"backpropagation.":[98],"first":[100],"apply":[101,176],"contextual":[105],"bandit":[106],"setting":[107],"optimize":[109,153],"reward":[111],"function":[112,157,169],"unknown":[115],"agent.":[118,174],"In":[119],"setting,":[121],"empirically":[123,189],"demonstrate":[124],"significantly":[127],"outperforms":[128],"REINFORCE,":[129],"indicating":[130],"reduction":[134],"implied":[135],"our":[137],"theoretical":[138],"analysis":[139],"significant":[141],"and":[142,188],"impactful.":[143],"then":[145],"show":[146,190],"how":[147],"can":[149,205],"be":[150],"extended":[151,178],"more":[155],"general":[156],"outputs":[160],"network":[163],"units,":[166],"where":[167],"known":[171],"version":[179],"train":[183],"variational":[186],"auto-encoder":[187],"it":[191],"compares":[192],"favourably":[193],"other":[195],"strong":[196],"methods.":[197],"believe":[199],"ideas":[202],"underlying":[203],"help":[206],"stimulate":[207],"new":[208],"ways":[209],"thinking":[211],"about":[212],"efficient":[213],"assignment":[215],"compute":[218],"graphs.":[219]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}