{"id":"https://openalex.org/W7124314667","doi":"https://doi.org/10.65109/izjf8295","title":"Reinforcement Learning Interventions on Boundedly Rational Human Agents in Frictionful Tasks","display_name":"Reinforcement Learning Interventions on Boundedly Rational Human Agents in Frictionful Tasks","publication_year":2024,"publication_date":"2024-05-06","ids":{"openalex":"https://openalex.org/W7124314667","doi":"https://doi.org/10.65109/izjf8295","pmid":"https://pubmed.ncbi.nlm.nih.gov/39381596","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/11460771"},"language":"en","primary_location":{"id":"doi:10.65109/izjf8295","doi":"https://doi.org/10.65109/izjf8295","is_oa":false,"landing_page_url":"https://doi.org/10.65109/izjf8295","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11460771/pdf/nihms-1970700.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093817171","display_name":"Eura Nofshin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eura Nofshin","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102978385","display_name":"Siddharth Swaroop","orcid":"https://orcid.org/0009-0009-5345-8844","observed_orcids":["https://orcid.org/0009-0009-5345-8844"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Swaroop","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110970401","display_name":"Weiwei Pan","orcid":"https://orcid.org/0009-0004-2688-0605","observed_orcids":["https://orcid.org/0009-0004-2688-0605"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiwei Pan","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070589969","display_name":"Susan A. Murphy","orcid":"https://orcid.org/0000-0002-2032-4286","observed_orcids":["https://orcid.org/0000-0002-2032-4286"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Susan Murphy","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038771285","display_name":"Finale Doshi\u2010Velez","orcid":"https://orcid.org/0000-0003-2886-3898","observed_orcids":["https://orcid.org/0000-0003-2886-3898"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Finale Doshi-Velez","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I136199984"],"apc_list":null,"apc_paid":null,"fwci":0.2937,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58458279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2024","issue":null,"first_page":"1482","last_page":"1491"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8154000043869019,"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":0.8154000043869019,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.1251000016927719,"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":0.007300000172108412,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/boundedly-rational-agents","display_name":"boundedly rational agents","score":0.6990000009536743},{"id":"https://openalex.org/keywords/planning-agents","display_name":"planning agents","score":0.578000009059906},{"id":"https://openalex.org/keywords/automated-planning","display_name":"automated planning","score":0.5720000267028809},{"id":"https://openalex.org/keywords/goal-directed-behavior","display_name":"goal-directed behavior","score":0.47200000286102295},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.4429999887943268},{"id":"https://openalex.org/keywords/discount-factor","display_name":"discount factor","score":0.5189999938011169}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7513999938964844},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6134999990463257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5242999792098999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4867999851703644},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4675000011920929},{"id":"https://openalex.org/C31772880","wikidata":"https://www.wikidata.org/wiki/Q2666479","display_name":"Rational agent","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.4106000065803528},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.37059998512268066},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C201717286","wikidata":"https://www.wikidata.org/wiki/Q938185","display_name":"Rationality","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C36375443","wikidata":"https://www.wikidata.org/wiki/Q7295774","display_name":"Rational planning model","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C117035363","wikidata":"https://www.wikidata.org/wiki/Q3769299","display_name":"Human behavior","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C27415008","wikidata":"https://www.wikidata.org/wiki/Q7256382","display_name":"Psychological intervention","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3075999915599823},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2615000009536743},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.65109/izjf8295","doi":"https://doi.org/10.65109/izjf8295","is_oa":false,"landing_page_url":"https://doi.org/10.65109/izjf8295","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"proceedings-article"},{"id":"pmid:39381596","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39381596","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ... International Joint Conference on Autonomous Agents and Multiagent Systems : AAMAS. International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11460771","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11460771","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11460771/pdf/nihms-1970700.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Proc Int Joint Conf Auton Agents Multiagent Syst","raw_type":"Text"},{"id":"pmh:oai:arXiv.org:2401.14923","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.14923","pdf_url":"https://arxiv.org/pdf/2401.14923","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.2401.14923","doi":"https://doi.org/10.48550/arxiv.2401.14923","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.14923","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:pubmedcentral.nih.gov:11460771","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11460771","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11460771/pdf/nihms-1970700.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Proc Int Joint Conf Auton Agents Multiagent Syst","raw_type":"Text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5059644240","display_name":"HCC: Medium: Improving Human-AI Collaboration on Decision-Making Tasks","funder_award_id":"2107391","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6181177137","display_name":"Graduate Research Fellowship Program (GRFP)","funder_award_id":"2140743","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G773633582","display_name":null,"funder_award_id":"P41EB028242","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8916974882","display_name":null,"funder_award_id":"DGE2140743","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G9000888489","display_name":"Center for Methodologies for Adapting and Personalizing Prevention, Treatment and Recovery Services for SUD and HIV (MAPS Center)","funder_award_id":"P50DA054039","funder_id":"https://openalex.org/F4320337347","funder_display_name":"National Institute on Drug Abuse"},{"id":"https://openalex.org/G9000916032","display_name":"mHealth Center for Discovery, Optimization, and Translation of Temporally-Precise Interventions (mDOT)","funder_award_id":"P41EB028242","funder_id":"https://openalex.org/F4320337363","funder_display_name":"National Institute of Biomedical Imaging and Bioengineering"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337347","display_name":"National Institute on Drug Abuse","ror":"https://ror.org/00fq5cm18"},{"id":"https://openalex.org/F4320337363","display_name":"National Institute of Biomedical Imaging and Bioengineering","ror":"https://ror.org/00372qc85"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7124314667.pdf","grobid_xml":"https://content.openalex.org/works/W7124314667.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W2794582352"],"related_works":["https://openalex.org/W4415230411","https://openalex.org/W7133581600","https://openalex.org/W7124314503","https://openalex.org/W3183390056","https://openalex.org/W2546792229","https://openalex.org/W7161170733","https://openalex.org/W7097966158","https://openalex.org/W2240391336","https://openalex.org/W4399970590","https://openalex.org/W3033617194"],"abstract_inverted_index":{"Many":[0],"important":[1],"behavior":[2],"changes":[3],"are":[4],"frictionful;":[5],"they":[6],"require":[7],"individuals":[8,32],"to":[9,30,34,52,87,105,115,118,153,169],"expend":[10],"effort":[11],"over":[12],"a":[13,69,81,88,100,133,147,173],"long":[14],"period":[15],"with":[16,163],"little":[17],"immediate":[18],"gratification.":[19],"Here,":[20],"an":[21,73,125],"artificial":[22],"intelligence":[23],"(AI)":[24],"agent":[25,42,75,102],"can":[26,167],"provide":[27],"personalized":[28],"interventions":[29],"help":[31,53],"stick":[33],"their":[35,119],"goals.":[36],"In":[37,59],"these":[38],"settings,":[39],"the":[40,47,56,78,96,116],"AI":[41,74,161],"must":[43],"personalize":[44],"rapidly":[45],"(before":[46],"individual":[48],"disengages)":[49],"and":[50,157],"interpretably,":[51],"us":[54,104],"understand":[55],"behavioral":[57],"interventions.":[58],"this":[60],"paper,":[61],"we":[62,131,155],"introduce":[63],"Behavior":[64],"Model":[65],"Reinforcement":[66],"Learning":[67],"(BMRL),":[68],"framework":[70],"in":[71,143],"which":[72],"intervenes":[76],"on":[77,172],"parameters":[79],"of":[80,95,135,149,176],"Markov":[82],"Decision":[83],"Process":[84],"(MDP)":[85],"belonging":[86],"boundedly":[89],"rational":[90],"human":[91,97,108,137,165],"agent.":[92],"Our":[93],"formulation":[94],"decision-maker":[98],"as":[99,124],"planning":[101,162],"allows":[103],"attribute":[106],"undesirable":[107],"policies":[109,171],"(ones":[110],"that":[111,139,160],"do":[112],"not":[113],"lead":[114,168],"goal)":[117],"maladapted":[120],"MDP":[121,150],"parameters,":[122],"such":[123],"extremely":[126],"low":[127],"discount":[128],"factor.":[129],"Furthermore,":[130],"propose":[132],"class":[134],"tractable":[136],"models":[138,166],"captures":[140],"fundamental":[141],"behaviors":[142],"frictionful":[144],"tasks.":[145],"Introducing":[146],"notion":[148],"equivalence":[151],"specific":[152],"BMRL,":[154],"theoretically":[156],"empirically":[158],"show":[159],"our":[164],"helpful":[170],"wide":[174],"range":[175],"more":[177],"complex,":[178],"ground-truth":[179],"humans.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2026-01-16T00:00:00"}