{"id":"https://openalex.org/W7140323116","doi":"https://doi.org/10.1007/s10009-026-00851-3","title":"Active discount factor elicitation via reward modification","display_name":"Active discount factor elicitation via reward modification","publication_year":2026,"publication_date":"2026-02-01","ids":{"openalex":"https://openalex.org/W7140323116","doi":"https://doi.org/10.1007/s10009-026-00851-3"},"language":"en","primary_location":{"id":"doi:10.1007/s10009-026-00851-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10009-026-00851-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10009-026-00851-3.pdf","source":{"id":"https://openalex.org/S122567160","display_name":"International Journal on Software Tools for Technology Transfer","issn_l":"1433-2779","issn":["1433-2779","1433-2787"],"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":"International Journal on Software Tools for Technology Transfer","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/s10009-026-00851-3.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008089103","display_name":"Shadi Tasdighi Kalat","orcid":"https://orcid.org/0000-0002-7339-6339"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shadi Tasdighi\u00a0Kalat","raw_affiliation_strings":["Department of Computer Science, University of Colorado Boulder, Boulder, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Colorado Boulder, Boulder, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040552045","display_name":"S. Sankaranarayanan","orcid":"https://orcid.org/0000-0001-6393-7413"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Sankaranarayanan","raw_affiliation_strings":["Department of Computer Science, University of Colorado Boulder, Boulder, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Colorado Boulder, Boulder, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130577629","display_name":"Ashutosh Trivedi","orcid":null},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashutosh Trivedi","raw_affiliation_strings":["Department of Computer Science, University of Colorado Boulder, Boulder, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Colorado Boulder, Boulder, USA","institution_ids":["https://openalex.org/I188538660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5008089103"],"corresponding_institution_ids":["https://openalex.org/I188538660"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31778896,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":"1","first_page":"55","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5546000003814697,"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":0.5546000003814697,"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/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.08990000188350677,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.039799999445676804,"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/preference-elicitation","display_name":"Preference elicitation","score":0.7226999998092651},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6184999942779541},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.6179999709129333},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6061999797821045},{"id":"https://openalex.org/keywords/discounting","display_name":"Discounting","score":0.5871999859809875},{"id":"https://openalex.org/keywords/time-preference","display_name":"Time preference","score":0.47380000352859497},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.4672999978065491},{"id":"https://openalex.org/keywords/theory-of-computation","display_name":"Theory of computation","score":0.44200000166893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7487999796867371},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.7226999998092651},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6184999942779541},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6179999709129333},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6061999797821045},{"id":"https://openalex.org/C6177178","wikidata":"https://www.wikidata.org/wiki/Q10998070","display_name":"Discounting","level":2,"score":0.5871999859809875},{"id":"https://openalex.org/C178562925","wikidata":"https://www.wikidata.org/wiki/Q186412","display_name":"Time preference","level":2,"score":0.47380000352859497},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.4672999978065491},{"id":"https://openalex.org/C24858836","wikidata":"https://www.wikidata.org/wiki/Q844718","display_name":"Theory of computation","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4374000132083893},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40689998865127563},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C2779785983","wikidata":"https://www.wikidata.org/wiki/Q5957248","display_name":"Hyperbolic discounting","level":3,"score":0.3580000102519989},{"id":"https://openalex.org/C2984634286","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision process","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C205706631","wikidata":"https://www.wikidata.org/wiki/Q2319304","display_name":"Expected utility hypothesis","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C72161134","wikidata":"https://www.wikidata.org/wiki/Q5421219","display_name":"Expert elicitation","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.26170000433921814},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.258899986743927}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10009-026-00851-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10009-026-00851-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10009-026-00851-3.pdf","source":{"id":"https://openalex.org/S122567160","display_name":"International Journal on Software Tools for Technology Transfer","issn_l":"1433-2779","issn":["1433-2779","1433-2787"],"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":"International Journal on Software Tools for Technology Transfer","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10009-026-00851-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10009-026-00851-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10009-026-00851-3.pdf","source":{"id":"https://openalex.org/S122567160","display_name":"International Journal on Software Tools for Technology Transfer","issn_l":"1433-2779","issn":["1433-2779","1433-2787"],"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":"International Journal on Software Tools for Technology Transfer","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G842143413","display_name":"CAREER: Reinforcement Learning for Recursive Markov Decision Processes and Beyond","funder_award_id":"2146563","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140323116.pdf","grobid_xml":"https://content.openalex.org/works/W7140323116.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1565850188","https://openalex.org/W1986389067","https://openalex.org/W2010887456","https://openalex.org/W2028560736","https://openalex.org/W2035338132","https://openalex.org/W2109304399","https://openalex.org/W2112074285","https://openalex.org/W2118208231","https://openalex.org/W2126953888","https://openalex.org/W2156738382","https://openalex.org/W2441241344","https://openalex.org/W2964350661","https://openalex.org/W2982316857","https://openalex.org/W3122286037","https://openalex.org/W3124158573","https://openalex.org/W3125118585","https://openalex.org/W3126024575","https://openalex.org/W4200056893","https://openalex.org/W4240615975","https://openalex.org/W4308643663","https://openalex.org/W4378675918"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Agent":[1],"behavior":[2],"is":[3,23],"shaped":[4],"by":[5],"latent":[6],"decision":[7],"parameters":[8],"that":[9,79,140],"govern":[10],"how":[11,95],"rewards":[12,122],"are":[13],"interpreted":[14],"and":[15,70,93,150,172,177],"traded":[16],"off":[17],"over":[18],"time.":[19],"A":[20],"key":[21],"example":[22],"the":[24,33,45,81],"discount":[25,34,59,84,133,170],"factor":[26,35,60],",":[27],"which":[28,116],"encodes":[29],"time":[30,49],"preference.":[31],"Mis-specifying":[32],"can":[36],"confound":[37],"reward-centric":[38],"behavioral":[39,174],"models":[40],"(e.g.,":[41],"inverse":[42],"RL),":[43],"motivating":[44],"need":[46],"to":[47,126,147],"infer":[48],"preference":[50],"directly":[51],"from":[52],"behavior.":[53],"This":[54],"paper":[55],"presents":[56],"methods":[57],"for":[58,168],"elicitation":[61,113,142],"in":[62,115,154],"finite-state":[63],"Markov":[64],"Decision":[65],"Processes":[66],"via":[67],"policy":[68],"observations":[69,96],"controlled":[71],"reward":[72,99,162],"modifications.":[73],"First,":[74],"we":[75,109,138],"introduce":[76],"an":[77,88,111,117],"algorithm":[78],"bounds":[80],"set":[82],"of":[83,130],"factors":[85,171],"consistent":[86],"with":[87],"agent\u2019s":[89,132],"observed":[90],"(near-)optimal":[91],"policy,":[92],"show":[94],"across":[97],"heterogeneous":[98],"settings":[100],"progressively":[101],"tighten":[102],"these":[103],"bounds.":[104],"Building":[105],"on":[106],"this":[107],"result,":[108],"propose":[110],"active":[112,141],"framework":[114],"ego":[118],"agent":[119],"strategically":[120],"adjusts":[121],"(with":[123],"fixed":[124],"dynamics)":[125],"refine":[127],"its":[128],"estimate":[129],"another":[131],"factor.":[134],"Through":[135],"case":[136],"studies,":[137],"demonstrate":[139],"accelerates":[143],"interval":[144],"refinement":[145],"relative":[146],"passive":[148],"observation":[149],"enables":[151],"targeted":[152],"exploration":[153],"strategic":[155],"multi-agent":[156],"settings.":[157],"Overall,":[158],"our":[159],"results":[160],"establish":[161],"modification":[163],"as":[164],"a":[165],"principled":[166],"mechanism":[167],"eliciting":[169],"improving":[173],"modeling,":[175],"prediction,":[176],"control.":[178]},"counts_by_year":[],"updated_date":"2026-05-23T06:10:36.450269","created_date":"2026-03-26T00:00:00"}