{"id":"https://openalex.org/W7123338831","doi":"https://doi.org/10.1109/cdc57313.2025.11312113","title":"Teaching Precommitted Agents: Model-Free Policy Evaluation and Control in Quasi-Hyperbolic Discounted MDPs","display_name":"Teaching Precommitted Agents: Model-Free Policy Evaluation and Control in Quasi-Hyperbolic Discounted MDPs","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123338831","doi":"https://doi.org/10.1109/cdc57313.2025.11312113"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5122844911","display_name":"S. R. Eshwar","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"S. R. Eshwar","raw_affiliation_strings":["Indian Institute of Science,Department of Computer Science and Automation,Bengaluru,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Department of Computer Science and Automation,Bengaluru,India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5122844911"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85797239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4161","last_page":"4166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.34869998693466187,"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":0.34869998693466187,"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":0.12890000641345978,"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/T11031","display_name":"Game Theory and Applications","score":0.07320000231266022,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6851999759674072},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6722999811172485},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6003999710083008},{"id":"https://openalex.org/keywords/discounting","display_name":"Discounting","score":0.5533000230789185},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5529000163078308},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.550599992275238},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5020999908447266}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6851999759674072},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6722999811172485},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503000259399414},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6003999710083008},{"id":"https://openalex.org/C6177178","wikidata":"https://www.wikidata.org/wiki/Q10998070","display_name":"Discounting","level":2,"score":0.5533000230789185},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5529000163078308},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.550599992275238},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5020999908447266},{"id":"https://openalex.org/C127729010","wikidata":"https://www.wikidata.org/wiki/Q60165","display_name":"Dynamic inconsistency","level":2,"score":0.41749998927116394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3813999891281128},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3506999909877777},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3409999907016754},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2962999939918518},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2777999937534332},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.2745000123977661},{"id":"https://openalex.org/C178562925","wikidata":"https://www.wikidata.org/wiki/Q186412","display_name":"Time preference","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8091235160827637}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Time-Inconsistent":[0],"preferences,":[1],"where":[2],"agents":[3,52],"favor":[4],"smaller-sooner":[5],"over":[6],"larger-later":[7],"rewards,":[8],"are":[9],"a":[10,22,80],"key":[11,45],"feature":[12],"of":[13,67],"human":[14],"and":[15,47,85,98],"animal":[16],"decision-making.":[17],"Quasi-Hyperbolic":[18],"(QH)":[19],"discounting":[20],"provides":[21],"simple":[23,81],"yet":[24],"powerful":[25],"model":[26],"for":[27,50,72,94,113],"this":[28,101],"behavior,":[29],"but":[30],"its":[31],"integration":[32],"into":[33],"the":[34,65,68,73,89],"reinforcement":[35],"learning":[36],"(RL)":[37],"framework":[38],"has":[39],"been":[40],"limited.":[41],"This":[42],"paper":[43],"addresses":[44],"theoretical":[46],"algorithmic":[48],"gaps":[49],"precommitted":[51],"with":[53,104],"QH":[54,115],"preferences.":[55],"We":[56],"make":[57],"two":[58],"primary":[59],"contributions:":[60],"(i)":[61],"we":[62,87],"formally":[63],"characterize":[64],"structure":[66],"optimal":[69],"policy,":[70],"proving":[71],"first":[74,90],"time":[75],"that":[76],"it":[77],"reduces":[78],"to":[79],"one-step":[82],"non-stationary":[83],"form;":[84],"(ii)":[86],"design":[88],"practical,":[91],"model-free":[92],"algorithms":[93],"both":[95,103],"policy":[96],"evaluation":[97],"Q-learning":[99],"in":[100,117],"setting,":[102],"provable":[105],"convergence":[106],"guarantees.":[107],"Our":[108],"results":[109],"provide":[110],"foundational":[111],"insights":[112],"incorporating":[114],"preferences":[116],"RL.":[118]},"counts_by_year":[],"updated_date":"2026-01-14T00:46:21.520733","created_date":"2026-01-14T00:00:00"}