{"id":"https://openalex.org/W4403503820","doi":"https://doi.org/10.1007/s10458-024-09682-5","title":"Formal contracts mitigate social dilemmas in multi-agent reinforcement learning","display_name":"Formal contracts mitigate social dilemmas in multi-agent reinforcement learning","publication_year":2024,"publication_date":"2024-10-18","ids":{"openalex":"https://openalex.org/W4403503820","doi":"https://doi.org/10.1007/s10458-024-09682-5"},"language":"en","primary_location":{"id":"doi:10.1007/s10458-024-09682-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-024-09682-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-024-09682-5.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"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":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10458-024-09682-5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074663019","display_name":"Andreas Haupt","orcid":"https://orcid.org/0000-0002-2952-4188"},"institutions":[{"id":"https://openalex.org/I126820664","display_name":"Vassar College","ror":"https://ror.org/022x6qg61","country_code":"US","type":"education","lineage":["https://openalex.org/I126820664"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andreas Haupt","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar Street, Cambridge, 02139, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar Street, Cambridge, 02139, MA, USA","institution_ids":["https://openalex.org/I126820664","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033339992","display_name":"Phillip Christoffersen","orcid":null},"institutions":[{"id":"https://openalex.org/I126820664","display_name":"Vassar College","ror":"https://ror.org/022x6qg61","country_code":"US","type":"education","lineage":["https://openalex.org/I126820664"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Phillip Christoffersen","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar Street, Cambridge, 02139, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar Street, Cambridge, 02139, MA, USA","institution_ids":["https://openalex.org/I126820664","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040083642","display_name":"Mehul Damani","orcid":"https://orcid.org/0000-0001-5790-376X"},"institutions":[{"id":"https://openalex.org/I126820664","display_name":"Vassar College","ror":"https://ror.org/022x6qg61","country_code":"US","type":"education","lineage":["https://openalex.org/I126820664"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehul Damani","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar Street, Cambridge, 02139, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar Street, Cambridge, 02139, MA, USA","institution_ids":["https://openalex.org/I126820664","https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076757561","display_name":"Dylan Hadfield-Menell","orcid":"https://orcid.org/0000-0002-6168-4763"},"institutions":[{"id":"https://openalex.org/I126820664","display_name":"Vassar College","ror":"https://ror.org/022x6qg61","country_code":"US","type":"education","lineage":["https://openalex.org/I126820664"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dylan Hadfield-Menell","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar Street, Cambridge, 02139, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar Street, Cambridge, 02139, MA, USA","institution_ids":["https://openalex.org/I126820664","https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033339992","https://openalex.org/A5074663019"],"corresponding_institution_ids":["https://openalex.org/I126820664","https://openalex.org/I63966007"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":1.0117,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.78767764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"38","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5960793495178223},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5749253034591675},{"id":"https://openalex.org/keywords/social-learning","display_name":"Social learning","score":0.5238925218582153},{"id":"https://openalex.org/keywords/social-dilemma","display_name":"Social dilemma","score":0.44612401723861694},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3736438751220703},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3554324507713318},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3235380947589874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2897142171859741},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.28600895404815674},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.23982611298561096}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5960793495178223},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5749253034591675},{"id":"https://openalex.org/C79416737","wikidata":"https://www.wikidata.org/wiki/Q2305519","display_name":"Social learning","level":2,"score":0.5238925218582153},{"id":"https://openalex.org/C187206662","wikidata":"https://www.wikidata.org/wiki/Q55607920","display_name":"Social dilemma","level":2,"score":0.44612401723861694},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3736438751220703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3554324507713318},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3235380947589874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2897142171859741},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.28600895404815674},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.23982611298561096}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10458-024-09682-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-024-09682-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-024-09682-5.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"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":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/157416","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/157416","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/157416/1/10458_2024_Article_9682.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Springer US","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1007/s10458-024-09682-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-024-09682-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-024-09682-5.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"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":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309369","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403503820.pdf","grobid_xml":"https://content.openalex.org/works/W4403503820.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1485535210","https://openalex.org/W1823691459","https://openalex.org/W2015007620","https://openalex.org/W2023067240","https://openalex.org/W2029050771","https://openalex.org/W2088956500","https://openalex.org/W2151408086","https://openalex.org/W2416397817","https://openalex.org/W2590517691","https://openalex.org/W2735995851","https://openalex.org/W2768978272","https://openalex.org/W2811374584","https://openalex.org/W2888078780","https://openalex.org/W2913525780","https://openalex.org/W2914559550","https://openalex.org/W2964262254","https://openalex.org/W2993335844","https://openalex.org/W2999905431","https://openalex.org/W3008369822","https://openalex.org/W3122162510","https://openalex.org/W3192756386","https://openalex.org/W4205912589","https://openalex.org/W4207074987","https://openalex.org/W4253299649","https://openalex.org/W4297974475","https://openalex.org/W4303111783","https://openalex.org/W4311573031","https://openalex.org/W4385767876","https://openalex.org/W4388596127","https://openalex.org/W6631422176","https://openalex.org/W6674639890","https://openalex.org/W6676468133","https://openalex.org/W6740801417","https://openalex.org/W6779372982","https://openalex.org/W6780396752"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2950219151","https://openalex.org/W2946123577","https://openalex.org/W3212652405","https://openalex.org/W2803797390"],"abstract_inverted_index":{"Abstract":[0],"Multi-agent":[1],"Reinforcement":[2],"Learning":[3],"(MARL)":[4],"is":[5,43],"a":[6,16,83,125,179],"powerful":[7],"tool":[8],"for":[9,135],"training":[10,180],"autonomous":[11],"agents":[12,75,87],"acting":[13],"independently":[14],"in":[15,47,54,76,172,195],"common":[17,210],"environment.":[18],"However,":[19],"it":[20],"can":[21],"lead":[22,147],"to":[23,49,70,82,90,148],"sub-optimal":[24],"behavior":[25],"when":[26],"individual":[27],"incentives":[28,31,73],"and":[29,102,139,209],"group":[30],"diverge.":[32],"Humans":[33],"are":[34,100,176],"remarkably":[35],"capable":[36],"at":[37],"solving":[38],"these":[39],"social":[40],"dilemmas.":[41],"It":[42],"an":[44,80,156],"open":[45],"problem":[46],"MARL":[48],"replicate":[50],"such":[51],"cooperative":[52],"behaviors":[53],"selfish":[55],"agents.":[56],"In":[57],"this":[58,108],"work,":[59],"we":[60,105,132],"draw":[61],"upon":[62],"the":[63,173],"idea":[64],"of":[65,93,114,129,170],"formal":[66],"contracting":[67,174],"from":[68],"economics":[69],"overcome":[71],"diverging":[72],"between":[74],"MARL.":[77],"We":[78,162,191],"propose":[79],"augmentation":[81,109,175],"Markov":[84,118],"game":[85],"where":[86],"voluntarily":[88],"agree":[89],"binding":[91],"transfers":[92],"reward,":[94],"under":[95,141],"pre-specified":[96],"conditions.":[97],"Our":[98],"contributions":[99],"theoretical":[101,165],"empirical.":[103],"First,":[104],"show":[106,133],"that":[107,134,204],"makes":[110],"all":[111,115],"subgame-perfect":[112],"equilibria":[113],"Fully":[116],"Observable":[117],"Games":[119],"exhibit":[120],"socially":[121],"optimal":[122],"behavior,":[123],"given":[124],"sufficiently":[126],"rich":[127],"space":[128,153],"contracts.":[130],"Next,":[131],"general":[136],"contract":[137,145,152],"spaces,":[138],"even":[140],"partial":[142],"observability,":[143],"richer":[144],"spaces":[146],"higher":[149],"welfare.":[150],"Hence,":[151],"design":[154],"solves":[155],"exploration-exploitation":[157],"tradeoff,":[158],"sidestepping":[159],"incentive":[160],"issues.":[161],"complement":[163],"our":[164,193],"analysis":[166],"with":[167],"experiments.":[168],"Issues":[169],"exploration":[171],"mitigated":[177],"using":[178],"methodology":[181,194],"inspired":[182],"by":[183],"multi-objective":[184],"reinforcement":[185],"learning:":[186],"Multi-Objective":[187],"Contract":[188],"Augmentation":[189],"Learning.":[190],"test":[192],"static,":[196],"single-move":[197],"games,":[198],"as":[199,201],"well":[200],"dynamic":[202],"domains":[203],"simulate":[205],"traffic,":[206],"pollution":[207],"management,":[208],"pool":[211],"resource":[212],"management.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}