{"id":"https://openalex.org/W4416123793","doi":"https://doi.org/10.48550/arxiv.2504.03743","title":"Modelling bounded rational decision-making through Wasserstein constraints","display_name":"Modelling bounded rational decision-making through Wasserstein constraints","publication_year":2025,"publication_date":"2025-04-01","ids":{"openalex":"https://openalex.org/W4416123793","doi":"https://doi.org/10.48550/arxiv.2504.03743"},"language":"en","primary_location":{"id":"pmh:oai:RePEc:arx:papers:2504.03743","doi":null,"is_oa":false,"landing_page_url":"http://arxiv.org/pdf/2504.03743","pdf_url":"http://arxiv.org/pdf/2504.03743","source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"preprint"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.03743","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014921421","display_name":"Benjamin Patrick Evans","orcid":"https://orcid.org/0000-0002-2466-5264","observed_orcids":["https://orcid.org/0000-0002-2466-5264"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Evans, Benjamin Patrick","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047729153","display_name":"Leo Ardon","orcid":"https://orcid.org/0000-0003-4400-7127","observed_orcids":["https://orcid.org/0000-0003-4400-7127"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ardon, Leo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081450666","display_name":"Sumitra Ganesh","orcid":"https://orcid.org/0000-0003-1695-8574","observed_orcids":["https://orcid.org/0000-0003-1695-8574"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ganesh, Sumitra","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9945999979972839,"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":0.9945999979972839,"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/T10315","display_name":"Decision-Making and Behavioral Economics","score":0.0017000000225380063,"subfield":{"id":"https://openalex.org/subfields/1800","display_name":"General Decision Sciences"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.000699999975040555,"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/bounded-rationality","display_name":"bounded rationality","score":0.9819999933242798},{"id":"https://openalex.org/keywords/wasserstein-distance","display_name":"Wasserstein distance","score":0.8569999933242798},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6650000214576721},{"id":"https://openalex.org/keywords/information-constraints","display_name":"information constraints","score":0.515999972820282},{"id":"https://openalex.org/keywords/prior-beliefs","display_name":"prior beliefs","score":0.6639999747276306},{"id":"https://openalex.org/keywords/kullback-leibler-divergence","display_name":"Kullback-Leibler divergence","score":0.7179999947547913},{"id":"https://openalex.org/keywords/mutual-information","display_name":"mutual information","score":0.9259999990463257},{"id":"https://openalex.org/keywords/entropy-information-theory","display_name":"entropy (information theory)","score":0.7670000195503235}],"concepts":[{"id":"https://openalex.org/C58694771","wikidata":"https://www.wikidata.org/wiki/Q814385","display_name":"Bounded rationality","level":2,"score":0.6671000123023987},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.6486999988555908},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5863999724388123},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5264999866485596},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.4950000047683716},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4742000102996826},{"id":"https://openalex.org/C21031990","wikidata":"https://www.wikidata.org/wiki/Q355020","display_name":"Probability measure","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.412200003862381},{"id":"https://openalex.org/C31772880","wikidata":"https://www.wikidata.org/wiki/Q2666479","display_name":"Rational agent","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.397599995136261},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.29510000348091125},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C2986046992","wikidata":"https://www.wikidata.org/wiki/Q16773055","display_name":"Information aggregation","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C87868495","wikidata":"https://www.wikidata.org/wiki/Q750843","display_name":"Information processing","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:RePEc:arx:papers:2504.03743","doi":null,"is_oa":false,"landing_page_url":"http://arxiv.org/pdf/2504.03743","pdf_url":"http://arxiv.org/pdf/2504.03743","source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"preprint"},{"id":"pmh:oai:arXiv.org:2504.03743","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.03743","pdf_url":"https://arxiv.org/pdf/2504.03743","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.03743","doi":"https://doi.org/10.48550/arxiv.2504.03743","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.03743","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.03743","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.03743","pdf_url":"https://arxiv.org/pdf/2504.03743","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modelling":[0],"bounded":[1,130],"rational":[2,131],"decision-making":[3,25],"through":[4],"information":[5,116],"constrained":[6],"processing":[7],"provides":[8],"a":[9,18,68],"principled":[10],"approach":[11,127,138,145],"for":[12,112,128,147],"representing":[13],"departures":[14],"from":[15],"rationality":[16],"within":[17],"reinforcement":[19],"learning":[20],"framework,":[21],"while":[22,167],"still":[23],"treating":[24],"as":[26,94],"an":[27,125],"optimization":[28],"process.":[29],"However,":[30],"existing":[31],"approaches":[32,51],"are":[33],"generally":[34],"based":[35],"on":[36,71],"Entropy,":[37],"Kullback-Leibler":[38],"divergence,":[39],"or":[40],"Mutual":[41,115],"Information.":[42],"In":[43],"this":[44,144],"work,":[45],"we":[46,123],"highlight":[47],"issues":[48],"with":[49,54],"these":[50],"when":[52],"dealing":[53],"ordinal":[55,151],"action":[56],"spaces.":[57],"Specifically,":[58],"entropy":[59],"assumes":[60],"uniform":[61],"prior":[62,174],"beliefs,":[63],"missing":[64],"the":[65,95,102,106,140,148],"impact":[66],"of":[67,80,82,97,150,160],"priori":[69],"biases":[70],"decision-makings.":[72],"KL-Divergence":[73],"addresses":[74],"this,":[75],"however,":[76],"has":[77,86],"no":[78],"notion":[79],"\"nearness\"":[81],"actions,":[83,152,166,172],"and":[84,99,158,176],"additionally,":[85],"several":[87],"well":[88],"known":[89],"potentially":[90],"undesirable":[91],"properties":[92],"such":[93],"lack":[96],"symmetry,":[98],"furthermore,":[100],"requires":[101],"distributions":[103],"to":[104,120,163,179],"have":[105],"same":[107],"support":[108],"(e.g.":[109],"positive":[110],"probability":[111,171],"all":[113],"actions).":[114],"is":[117,177],"often":[118],"difficult":[119],"estimate.":[121],"Here,":[122],"propose":[124],"alternative":[126],"modeling":[129,153],"RL":[132],"agents":[133],"utilising":[134],"Wasserstein":[135],"distances.":[136],"This":[137],"overcomes":[139],"aforementioned":[141],"issues.":[142],"Crucially,":[143],"accounts":[146],"nearness":[149],"\"stickiness\"":[154],"in":[155],"agent":[156],"decisions":[157],"unlikeliness":[159],"rapidly":[161],"switching":[162],"far":[164],"away":[165],"also":[168],"supporting":[169],"low":[170],"zero-support":[173],"distributions,":[175],"simple":[178],"calculate":[180],"directly.":[181]},"counts_by_year":[],"updated_date":"2026-10-04T09:36:47.201465","created_date":"2025-10-10T00:00:00"}