{"id":"https://openalex.org/W4399554010","doi":"https://doi.org/10.48550/arxiv.2406.06041","title":"Risk Sensitivity in Markov Games and Multi-Agent Reinforcement Learning: A Systematic Review","display_name":"Risk Sensitivity in Markov Games and Multi-Agent Reinforcement Learning: A Systematic Review","publication_year":2024,"publication_date":"2024-06-10","ids":{"openalex":"https://openalex.org/W4399554010","doi":"https://doi.org/10.48550/arxiv.2406.06041"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.06041","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.06041","pdf_url":"https://arxiv.org/pdf/2406.06041","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"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"},"volume":null,"type":"review","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.06041","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036040705","display_name":"Hafez Ghaemi","orcid":"https://orcid.org/0000-0001-6326-5258","observed_orcids":["https://orcid.org/0000-0001-6326-5258"]},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Ghaemi, Hafez","raw_affiliation_strings":["School of Electrical and Computer Engineering , University of Tehran , Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering , University of Tehran , Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099096851","display_name":"Shirin Jamshidi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Jamshidi, Shirin","raw_affiliation_strings":["School of Electrical and Computer Engineering , University of Tehran , Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering , University of Tehran , Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099096852","display_name":"Mohammad Mashreghi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mashreghi, Mohammad","raw_affiliation_strings":["School of Electrical and Computer Engineering , University of Tehran , Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering , University of Tehran , Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072135442","display_name":"Majid Nili Ahmadabadi","orcid":"https://orcid.org/0000-0002-6370-6057","observed_orcids":["https://orcid.org/0000-0002-6370-6057"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmadabadi, Majid Nili","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081002970","display_name":"Hamed Kebriaei","orcid":"https://orcid.org/0000-0002-3781-2163","observed_orcids":["https://orcid.org/0000-0002-3781-2163"]},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Kebriaei, Hamed","raw_affiliation_strings":["School of Electrical and Computer Engineering , University of Tehran , Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering , University of Tehran , Iran","institution_ids":["https://openalex.org/I23946033"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.024,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.12459807,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"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":0.9570000171661377,"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":0.9570000171661377,"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/T11031","display_name":"Game Theory and Applications","score":0.03020000085234642,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0032999999821186066,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.9079999923706055},{"id":"https://openalex.org/keywords/risk-measures","display_name":"risk measures","score":0.9950000047683716},{"id":"https://openalex.org/keywords/risk-preferences","display_name":"risk preferences","score":0.6589999794960022},{"id":"https://openalex.org/keywords/multi-agent-decision-making","display_name":"multi-agent decision making","score":0.75},{"id":"https://openalex.org/keywords/behavioral-economics","display_name":"behavioral economics","score":0.6420000195503235},{"id":"https://openalex.org/keywords/game-theory","display_name":"game theory","score":0.3799999952316284}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7455538511276245},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.6152370572090149},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.592951774597168},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5072504878044128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5071408748626709},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.42480435967445374},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3478814959526062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31979459524154663},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.296550989151001},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15566128492355347},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14414545893669128},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10176903009414673},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07505032420158386},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.06041","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.06041","pdf_url":"https://arxiv.org/pdf/2406.06041","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"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":"doi:10.48550/arxiv.2406.06041","doi":"https://doi.org/10.48550/arxiv.2406.06041","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.06041","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.06041","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.06041","pdf_url":"https://arxiv.org/pdf/2406.06041","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"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"},"sustainable_development_goals":[],"study_designs":[{"id":"https://openalex.org/study-designs/systematic-review","display_name":"Systematic Review"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399554010.pdf","grobid_xml":"https://content.openalex.org/works/W4399554010.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W2173248099","https://openalex.org/W3107615218","https://openalex.org/W3169011731","https://openalex.org/W4289358754","https://openalex.org/W4410985964"],"related_works":["https://openalex.org/W7133189170","https://openalex.org/W7124321218","https://openalex.org/W4396717816","https://openalex.org/W4221161029","https://openalex.org/W3082864503","https://openalex.org/W3174819736","https://openalex.org/W2945449812","https://openalex.org/W7132655580","https://openalex.org/W7129179798","https://openalex.org/W4417438531"],"abstract_inverted_index":{"Markov":[0],"games":[1],"(MGs)":[2],"and":[3,22,73,105,120,135,140,149,151,168,174],"multi-agent":[4,15],"reinforcement":[5,133],"learning":[6,134],"(MARL)":[7],"are":[8,29,80],"studied":[9],"to":[10,31,59,85,102],"model":[11],"decision":[12,63],"making":[13,64],"in":[14,20,65,69,118,126,147,166,171],"systems.":[16],"Traditionally,":[17],"the":[18,93,100,113,172],"objective":[19,95],"MG":[21,104,119,148],"MARL":[23,121,150],"has":[24,123],"been":[25,124],"risk-neutral,":[26],"i.e.,":[27],"agents":[28],"assumed":[30],"optimize":[32],"a":[33,87],"performance":[34],"metric":[35],"such":[36,56],"as":[37],"expected":[38],"return,":[39],"without":[40],"taking":[41],"into":[42,92],"account":[43],"subjective":[44],"or":[45,50],"cognitive":[46],"preferences":[47,57,79],"of":[48,51,62,90,96,132,178],"themselves":[49],"other":[52,130],"agents.":[53],"However,":[54],"ignoring":[55],"leads":[58],"inaccurate":[60],"models":[61],"many":[66],"real-world":[67],"scenarios":[68],"finance,":[70],"operations":[71],"research,":[72],"behavioral":[74],"economics.":[75],"Therefore,":[76],"when":[77],"these":[78],"present,":[81],"it":[82],"is":[83],"necessary":[84],"incorporate":[86,159],"suitable":[88],"measure":[89],"risk":[91,116,144],"optimization":[94],"agents,":[97],"which":[98],"opens":[99],"door":[101],"risk-sensitive":[103],"MARL.":[106],"In":[107],"this":[108],"paper,":[109],"we":[110,162],"systemically":[111],"review":[112],"literature":[114],"on":[115],"sensitivity":[117],"that":[122,158],"growing":[125],"recent":[127,164],"years":[128],"alongside":[129],"areas":[131],"game":[136],"theory.":[137],"We":[138],"define":[139],"mathematically":[141],"describe":[142],"different":[143],"measures":[145],"used":[146],"individually":[152],"for":[153],"each":[154],"measure,":[155],"discuss":[156,175],"articles":[157],"it.":[160],"Finally,":[161],"identify":[163],"trends":[165],"theoretical":[167],"applied":[169],"works":[170],"field":[173],"possible":[176],"directions":[177],"future":[179],"research.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-06-12T00:00:00"}