{"id":"https://openalex.org/W2999329929","doi":null,"title":"Inducing Cooperation in Multi-Agent Games Through Status-Quo Loss.","display_name":"Inducing Cooperation in Multi-Agent Games Through Status-Quo Loss.","publication_year":2020,"publication_date":"2020-01-15","ids":{"openalex":"https://openalex.org/W2999329929","mag":"2999329929"},"language":"en","primary_location":{"id":"mag:2999329929","doi":null,"is_oa":false,"landing_page_url":"http://export.arxiv.org/pdf/2001.05458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000852149","display_name":"Pinkesh Badjatiya","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pinkesh Badjatiya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112660758","display_name":"Mausoom Sarkar","orcid":"https://orcid.org/0009-0005-0387-1674","observed_orcids":["https://orcid.org/0009-0005-0387-1674"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mausoom Sarkar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101789171","display_name":"Abhishek Sinha","orcid":"https://orcid.org/0000-0002-3598-480X","observed_orcids":["https://orcid.org/0000-0002-3598-480X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhishek Sinha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012548250","display_name":"Siddharth Singh","orcid":"https://orcid.org/0000-0003-1699-2561","observed_orcids":["https://orcid.org/0000-0003-1699-2561","https://orcid.org/0000-0002-2259-8790"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siddharth Singh","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1699-2561","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051210766","display_name":"Nikaash Puri","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikaash Puri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081562101","display_name":"Balaji Krishnamurthy","orcid":"https://orcid.org/0000-0003-0464-536X","observed_orcids":["https://orcid.org/0000-0003-0464-536X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Balaji Krishnamurthy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0844,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.40385899,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":92},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9160000085830688,"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":0.9160000085830688,"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.04410000145435333,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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":0.0142000000923872,"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/multi-agent-games","display_name":"multi-agent games","score":0.6570000052452087},{"id":"https://openalex.org/keywords/social-dilemmas","display_name":"social dilemmas","score":0.8560000061988831},{"id":"https://openalex.org/keywords/cooperation","display_name":"cooperation","score":0.8650000095367432},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.7860000133514404},{"id":"https://openalex.org/keywords/individual-rationality","display_name":"individual rationality","score":0.7110000252723694},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.8429999947547913},{"id":"https://openalex.org/keywords/visual-games","display_name":"visual games","score":0.3499999940395355}],"concepts":[{"id":"https://openalex.org/C2776748549","wikidata":"https://www.wikidata.org/wiki/Q201610","display_name":"Status quo","level":2,"score":0.9164004921913147},{"id":"https://openalex.org/C187206662","wikidata":"https://www.wikidata.org/wiki/Q55607920","display_name":"Social dilemma","level":2,"score":0.9116405248641968},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.818885326385498},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6843923330307007},{"id":"https://openalex.org/C201717286","wikidata":"https://www.wikidata.org/wiki/Q938185","display_name":"Rationality","level":2,"score":0.5714011192321777},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49428892135620117},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.43175849318504333},{"id":"https://openalex.org/C113494165","wikidata":"https://www.wikidata.org/wiki/Q41693","display_name":"Prisoner's dilemma","level":3,"score":0.4157883822917938},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.37198951840400696},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.34513914585113525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32676219940185547},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3164709806442261},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.21664172410964966},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.20994558930397034},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.08636295795440674},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0813463032245636},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2999329929","doi":null,"is_oa":false,"landing_page_url":"http://export.arxiv.org/pdf/2001.05458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3005802885","https://openalex.org/W3126649026","https://openalex.org/W2730328371","https://openalex.org/W2594794854","https://openalex.org/W2913294020","https://openalex.org/W2997338169","https://openalex.org/W3158207331","https://openalex.org/W4293875048","https://openalex.org/W7076000553","https://openalex.org/W345119801"],"abstract_inverted_index":{"In":[0],"social":[1,21,39,81,88,112],"dilemma":[2,82,89,113],"situations,":[3],"individual":[4,35],"rationality":[5],"leads":[6],"to":[7,26,33,42,57,59,103,120],"sub-optimal":[8],"group":[9],"outcomes.":[10],"Several":[11],"human":[12],"engagements":[13],"can":[14],"be":[15],"modeled":[16],"as":[17],"a":[18,49,111],"sequential":[19,38],"(multi-step)":[20],"dilemmas.":[22],"However,":[23],"in":[24,37,79,129],"contrast":[25],"humans,":[27],"Deep":[28],"Reinforcement":[29],"Learning":[30],"agents":[31,72,123],"trained":[32,73],"optimize":[34],"rewards":[36],"dilemmas":[40],"converge":[41],"selfish,":[43],"mutually":[44],"harmful":[45],"behavior.":[46],"We":[47,69,115],"introduce":[48],"status-quo":[50],"loss":[51],"(SQLoss)":[52],"that":[53,91],"encourages":[54],"an":[55],"agent":[56],"stick":[58],"the":[60,130],"status":[61],"quo,":[62],"rather":[63],"than":[64],"repeatedly":[65],"changing":[66],"its":[67],"policy.":[68],"show":[70,121],"how":[71,122],"with":[74,87],"SQLoss":[75,119],"evolve":[76,124],"cooperative":[77,106,127],"behavior":[78,128],"several":[80],"matrix":[83],"games.":[84],"To":[85],"work":[86],"games":[90],"have":[92],"visual":[93],"input,":[94],"we":[95],"propose":[96],"GameDistill.":[97],"GameDistill":[98,117],"uses":[99],"self-supervision":[100],"and":[101,107,118],"clustering":[102],"automatically":[104],"extract":[105],"selfish":[108],"policies":[109],"from":[110],"game.":[114],"combine":[116],"socially":[125],"desirable":[126],"Coin":[131],"Game.":[132]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2020-01-23T00:00:00"}