{"id":"https://openalex.org/W3114444335","doi":"https://doi.org/10.1007/s00521-022-07960-5","title":"Difference rewards policy gradients","display_name":"Difference rewards policy gradients","publication_year":2022,"publication_date":"2022-11-11","ids":{"openalex":"https://openalex.org/W3114444335","doi":"https://doi.org/10.1007/s00521-022-07960-5","mag":"3114444335","pmid":"https://pubmed.ncbi.nlm.nih.gov/40584428"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-022-07960-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-022-07960-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-022-07960-5.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-022-07960-5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068772408","display_name":"Jacopo Castellini","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jacopo Castellini","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Liverpool, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Liverpool, UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048451922","display_name":"Sam Devlin","orcid":"https://orcid.org/0000-0002-7769-3090"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sam Devlin","raw_affiliation_strings":["Microsoft Research Cambridge, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009493909","display_name":"Frans A. Oliehoek","orcid":"https://orcid.org/0000-0003-4372-5055"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Frans A. Oliehoek","raw_affiliation_strings":["Interactive Intelligence Group, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Intelligence Group, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084692264","display_name":"Rahul Savani","orcid":"https://orcid.org/0000-0003-1262-7831"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rahul Savani","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Liverpool, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Liverpool, UK","institution_ids":["https://openalex.org/I146655781"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068772408"],"corresponding_institution_ids":["https://openalex.org/I146655781"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.9714,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78715884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"37","issue":"19","first_page":"13163","last_page":"13186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9814000129699707,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.8584088087081909},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7948980331420898},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7297902703285217},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6232234835624695},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.564316987991333},{"id":"https://openalex.org/keywords/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.5464814901351929},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5449666976928711},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5040532350540161},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4150931239128113},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3719541132450104},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17657926678657532},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15318545699119568},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09885308146476746},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.08429181575775146}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.8584088087081909},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7948980331420898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7297902703285217},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6232234835624695},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.564316987991333},{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.5464814901351929},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5449666976928711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5040532350540161},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4150931239128113},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3719541132450104},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17657926678657532},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15318545699119568},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09885308146476746},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08429181575775146},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1007/s00521-022-07960-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-022-07960-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-022-07960-5.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},{"id":"pmid:40584428","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40584428","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":"Neural computing & applications","raw_type":null},{"id":"pmh:oai:arXiv.org:2012.11258","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.11258","pdf_url":"https://arxiv.org/pdf/2012.11258","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:europepmc.org:11012241","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12204931","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"},{"id":"pmh:oai:tudelft.nl:uuid:b47d136e-6080-4876-a299-43c68d7ff46e","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:b47d136e-6080-4876-a299-43c68d7ff46e","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"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":"","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1007/s00521-022-07960-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-022-07960-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-022-07960-5.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1073366937","display_name":"Influence-based Decision-making in Uncertain Environments","funder_award_id":"758824","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G1710232961","display_name":null,"funder_award_id":"EP/R001227/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G221468001","display_name":null,"funder_award_id":"First Grant EP/R001227/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3903193521","display_name":null,"funder_award_id":"758824","funder_id":"https://openalex.org/F4320335254","funder_display_name":"Horizon 2020"},{"id":"https://openalex.org/G7072063281","display_name":"Learning to Efficiently Plan in Flexible Distributed Organizations","funder_award_id":"EP/R001227/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320335254","display_name":"Horizon 2020","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3114444335.pdf","grobid_xml":"https://content.openalex.org/works/W3114444335.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W95906244","https://openalex.org/W178169250","https://openalex.org/W285701945","https://openalex.org/W600489529","https://openalex.org/W1515851193","https://openalex.org/W1521003796","https://openalex.org/W1583837637","https://openalex.org/W1590759229","https://openalex.org/W1641379095","https://openalex.org/W1969302761","https://openalex.org/W1980358463","https://openalex.org/W1981276685","https://openalex.org/W2009303086","https://openalex.org/W2012812921","https://openalex.org/W2026662445","https://openalex.org/W2061902782","https://openalex.org/W2096145798","https://openalex.org/W2099618002","https://openalex.org/W2104602264","https://openalex.org/W2104689655","https://openalex.org/W2107726111","https://openalex.org/W2108682071","https://openalex.org/W2118318536","https://openalex.org/W2119717200","https://openalex.org/W2122763142","https://openalex.org/W2132211083","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2161061197","https://openalex.org/W2171234133","https://openalex.org/W2189058185","https://openalex.org/W2209553695","https://openalex.org/W2292533394","https://openalex.org/W2396331870","https://openalex.org/W2539402368","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2768629321","https://openalex.org/W2891663723","https://openalex.org/W2892013712","https://openalex.org/W2914584698","https://openalex.org/W2932081708","https://openalex.org/W2950872548","https://openalex.org/W2962938168","https://openalex.org/W2963407617","https://openalex.org/W2963572325","https://openalex.org/W2963923407","https://openalex.org/W2964043796","https://openalex.org/W2981038142","https://openalex.org/W3010758700","https://openalex.org/W3041202696","https://openalex.org/W3044976552","https://openalex.org/W6600339963"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W2768629321","https://openalex.org/W4384574988","https://openalex.org/W2130711276","https://openalex.org/W4321463377","https://openalex.org/W3088331655","https://openalex.org/W4308828368"],"abstract_inverted_index":{"Abstract":[0],"Policy":[1],"gradient":[2],"methods":[3,30],"have":[4],"become":[5],"one":[6],"of":[7,12,28,120,123],"the":[8,40,75,82,92,111,118,136],"most":[9],"popular":[10],"classes":[11],"algorithms":[13],"for":[14,46,70],"multi-agent":[15,32,99],"reinforcement":[16],"learning.":[17],"A":[18],"key":[19],"challenge,":[20],"however,":[21],"that":[22,57,125,131],"is":[23,31,44,78,114,132],"not":[24],"addressed":[25],"by":[26,61,97],"many":[27],"these":[29],"credit":[33],"assignment:":[34],"assessing":[35],"an":[36,127],"agent\u2019s":[37],"contribution":[38],"to":[39,68,134],"overall":[41],"performance,":[42],"which":[43],"crucial":[45],"learning":[47,71,91],"good":[48],"policies.":[49],"We":[50],"propose":[51],"a":[52,103,121],"novel":[53],"algorithm":[54],"called":[55],"Dr.Reinforce":[56,86,124],"explicitly":[58],"tackles":[59],"this":[60],"combining":[62],"difference":[63,105,137],"rewards":[64,106],"with":[65,90],"policy":[66,100],"gradients":[67,101],"allow":[69],"decentralized":[72],"policies":[73],"when":[74],"reward":[76,83,112,129],"function":[77,84,113],"known.":[79],"By":[80],"differencing":[81],"directly,":[85],"avoids":[87],"difficulties":[88],"associated":[89],"Q":[93],"-function":[94],"as":[95],"done":[96],"counterfactual":[98],"(COMA),":[102],"state-of-the-art":[104],"method.":[107],"For":[108],"applications":[109],"where":[110],"unknown,":[115],"we":[116],"show":[117],"effectiveness":[119],"version":[122],"learns":[126],"additional":[128],"network":[130],"used":[133],"estimate":[135],"rewards.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}