{"id":"https://openalex.org/W4361273506","doi":"https://doi.org/10.3390/systems11040180","title":"It\u2019s All about Reward: Contrasting Joint Rewards and Individual Reward in Centralized Learning Decentralized Execution Algorithms","display_name":"It\u2019s All about Reward: Contrasting Joint Rewards and Individual Reward in Centralized Learning Decentralized Execution Algorithms","publication_year":2023,"publication_date":"2023-03-30","ids":{"openalex":"https://openalex.org/W4361273506","doi":"https://doi.org/10.3390/systems11040180"},"language":"en","primary_location":{"id":"doi:10.3390/systems11040180","is_oa":true,"landing_page_url":"https://doi.org/10.3390/systems11040180","pdf_url":"https://www.mdpi.com/2079-8954/11/4/180/pdf?version=1680836211","source":{"id":"https://openalex.org/S4210219410","display_name":"Systems","issn_l":"2079-8954","issn":["2079-8954"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2079-8954/11/4/180/pdf?version=1680836211","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086012093","display_name":"Peter Atrazhev","orcid":"https://orcid.org/0000-0002-2572-529X"},"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":false,"raw_author_name":"Peter Atrazhev","raw_affiliation_strings":["Electrical and Computer Engineering, University of Alberta, Edmonton, AB T6G 1H9, Canada"],"raw_orcid":"https://orcid.org/0000-0002-2572-529X","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Alberta, Edmonton, AB T6G 1H9, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090314619","display_name":"Petr Mus\u0131\u0301lek","orcid":"https://orcid.org/0000-0002-7780-5048"},"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":"Petr Musilek","raw_affiliation_strings":["Electrical and Computer Engineering, University of Alberta, Edmonton, AB T6G 1H9, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7780-5048","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Alberta, Edmonton, AB T6G 1H9, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5090314619"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":0.3313,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62755472,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"11","issue":"4","first_page":"180","last_page":"180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9926999807357788,"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":0.9926999807357788,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.955299973487854,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7338359355926514},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.733291506767273},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6689801216125488},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6123309135437012},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5786193013191223},{"id":"https://openalex.org/keywords/foraging","display_name":"Foraging","score":0.5314280986785889},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4906810522079468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4859949052333832},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4388866424560547},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10746783018112183}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7338359355926514},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.733291506767273},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6689801216125488},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6123309135437012},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5786193013191223},{"id":"https://openalex.org/C165287380","wikidata":"https://www.wikidata.org/wiki/Q2916569","display_name":"Foraging","level":2,"score":0.5314280986785889},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4906810522079468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4859949052333832},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4388866424560547},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10746783018112183},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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":3,"locations":[{"id":"doi:10.3390/systems11040180","is_oa":true,"landing_page_url":"https://doi.org/10.3390/systems11040180","pdf_url":"https://www.mdpi.com/2079-8954/11/4/180/pdf?version=1680836211","source":{"id":"https://openalex.org/S4210219410","display_name":"Systems","issn_l":"2079-8954","issn":["2079-8954"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8d7694b4bdf947ccbf92fc5c5ad6b413","is_oa":true,"landing_page_url":"https://doaj.org/article/8d7694b4bdf947ccbf92fc5c5ad6b413","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":"Systems, Vol 11, Iss 4, p 180 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2079-8954/11/4/180/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/systems11040180","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Systems","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/systems11040180","is_oa":true,"landing_page_url":"https://doi.org/10.3390/systems11040180","pdf_url":"https://www.mdpi.com/2079-8954/11/4/180/pdf?version=1680836211","source":{"id":"https://openalex.org/S4210219410","display_name":"Systems","issn_l":"2079-8954","issn":["2079-8954"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5150055381","display_name":null,"funder_award_id":"IT28020","funder_id":"https://openalex.org/F4320322675","funder_display_name":"Mitacs"}],"funders":[{"id":"https://openalex.org/F4320322675","display_name":"Mitacs","ror":"https://ror.org/00cjrc276"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4361273506.pdf"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1969302761","https://openalex.org/W2104689655","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2171863654","https://openalex.org/W2260756217","https://openalex.org/W2341435337","https://openalex.org/W2623431351","https://openalex.org/W2747213132","https://openalex.org/W2794643322","https://openalex.org/W2964043796","https://openalex.org/W3034941755","https://openalex.org/W3127463339","https://openalex.org/W3134226813","https://openalex.org/W3171124906","https://openalex.org/W4312374764","https://openalex.org/W6758846586","https://openalex.org/W6791533262"],"related_works":["https://openalex.org/W4200081355","https://openalex.org/W3081944365","https://openalex.org/W2135179174","https://openalex.org/W1932300341","https://openalex.org/W2294784349","https://openalex.org/W2890381285","https://openalex.org/W1979659965","https://openalex.org/W2136432055","https://openalex.org/W301102721","https://openalex.org/W2048910501"],"abstract_inverted_index":{"This":[0,103],"paper":[1],"addresses":[2],"the":[3,37,41,96,108,112],"issue":[4],"of":[5,18,31,39,95,110,114],"choosing":[6],"an":[7],"appropriate":[8],"reward":[9,42,116],"function":[10,43,117],"in":[11,54],"multi-agent":[12,122],"reinforcement":[13,123],"learning.":[14],"The":[15,34,77],"traditional":[16],"approach":[17],"using":[19],"joint":[20,45,75],"rewards":[21,64],"for":[22],"team":[23],"performance":[24],"is":[25],"questioned":[26],"due":[27],"to":[28,46,74,99],"a":[29,55,115],"lack":[30],"theoretical":[32],"backing.":[33],"authors":[35],"explore":[36],"impact":[38,120],"changing":[40],"from":[44],"individual":[47,63],"on":[48,107,121],"learning":[49,124],"centralized":[50],"decentralized":[51],"execution":[52],"algorithms":[53,82],"Level-Based":[56],"Foraging":[57],"environment.":[58],"Empirical":[59],"results":[60],"reveal":[61],"that":[62,80],"contain":[65],"more":[66],"variance,":[67],"but":[68],"may":[69],"have":[70],"less":[71],"bias":[72],"compared":[73],"rewards.":[76],"findings":[78],"show":[79],"different":[81],"are":[83],"affected":[84],"differently,":[85],"with":[86],"value":[87],"factorization":[88],"methods":[89,92],"and":[90,118],"PPO-based":[91],"taking":[93],"advantage":[94],"increased":[97],"variance":[98],"achieve":[100],"better":[101],"performance.":[102],"study":[104],"sheds":[105],"light":[106],"importance":[109],"considering":[111],"choice":[113],"its":[119],"systems.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2023-03-31T00:00:00"}