{"id":"https://openalex.org/W7123356380","doi":"https://doi.org/10.1109/cdc57313.2025.11312058","title":"Plan for the Worst with Advice: Advice-augmented Robust Markov Decision Processes","display_name":"Plan for the Worst with Advice: Advice-augmented Robust Markov Decision Processes","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123356380","doi":"https://doi.org/10.1109/cdc57313.2025.11312058"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312058","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":"conference-paper","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/A5074817934","display_name":"Tinashe Handina","orcid":null},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tinashe Handina","raw_affiliation_strings":["California Institute of Technology,Department of Computing and Mathematical Sciences,Pasadena,CA,USA,91125"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Institute of Technology,Department of Computing and Mathematical Sciences,Pasadena,CA,USA,91125","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005536479","display_name":"Kishan Panaganti","orcid":"https://orcid.org/0000-0001-9746-698X"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kishan Panaganti","raw_affiliation_strings":["California Institute of Technology,Department of Computing and Mathematical Sciences,Pasadena,CA,USA,91125"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Institute of Technology,Department of Computing and Mathematical Sciences,Pasadena,CA,USA,91125","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093925471","display_name":"Eric Mazumdar","orcid":null},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Mazumdar","raw_affiliation_strings":["California Institute of Technology,Department of Computing and Mathematical Sciences,Pasadena,CA,USA,91125"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Institute of Technology,Department of Computing and Mathematical Sciences,Pasadena,CA,USA,91125","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062565732","display_name":"Adam Wierman","orcid":"https://orcid.org/0000-0002-5923-0199"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Wierman","raw_affiliation_strings":["California Institute of Technology,Department of Computing and Mathematical Sciences,Pasadena,CA,USA,91125"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Institute of Technology,Department of Computing and Mathematical Sciences,Pasadena,CA,USA,91125","institution_ids":["https://openalex.org/I122411786"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I122411786"],"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":"4182","last_page":"4187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6636999845504761,"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":0.6636999845504761,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.23029999434947968,"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/T11031","display_name":"Game Theory and Applications","score":0.018200000748038292,"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/ambiguity","display_name":"Ambiguity","score":0.661899983882904},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6610000133514404},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.586899995803833},{"id":"https://openalex.org/keywords/decision-maker","display_name":"Decision maker","score":0.532800018787384},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.47749999165534973},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.4580000042915344},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.40779998898506165},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.40139999985694885}],"concepts":[{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.661899983882904},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6610000133514404},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.586899995803833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5379999876022339},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5365999937057495},{"id":"https://openalex.org/C2986080485","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision maker","level":2,"score":0.532800018787384},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.47749999165534973},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.4580000042915344},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.3747999966144562},{"id":"https://openalex.org/C2779955035","wikidata":"https://www.wikidata.org/wiki/Q4686785","display_name":"Advice (programming)","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C150325174","wikidata":"https://www.wikidata.org/wiki/Q4335500","display_name":"Optimal decision","level":3,"score":0.3449999988079071},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.3206999897956848},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3098999857902527},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C186116695","wikidata":"https://www.wikidata.org/wiki/Q5249226","display_name":"Decision analysis","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2808000147342682},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2806999981403351}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312058","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":[{"score":0.7790378332138062,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"consider":[1],"the":[2,13,39,49,57,88,103,128,131,181],"integration":[3],"of":[4,59,111,142],"advice":[5,55,92],"into":[6],"Robust":[7],"Markov":[8],"Decision":[9],"Processes":[10],"(RMDPs).":[11],"While":[12],"RMDP":[14],"formulation":[15],"aids":[16],"in":[17,47,56,75,173,180],"modeling":[18],"ambiguity":[19,129,179],"with":[20,118],"respect":[21,119],"to":[22,30,54,66,68,120],"transition":[23,62,93],"dynamics,":[24],"it":[25],"is":[26],"overly":[27],"conservative":[28],"due":[29],"its":[31],"focus":[32],"on":[33,127],"worst-case":[34,40],"instances.":[35],"To":[36],"move":[37],"beyond":[38],"framework,":[41],"we":[42,96,145,161],"propose":[43,108],"an":[44],"advice-augmented":[45],"setting":[46,77],"which":[48],"decision":[50,73,104],"maker":[51,74,105],"has":[52],"access":[53],"form":[58],"a":[60,81,109,140,148],"predicted":[61],"kernel":[63],"they":[64],"seek":[65],"leverage":[67],"obtain":[69],"better":[70],"guarantees.":[71],"The":[72],"this":[76,166],"cares":[78],"about":[79],"finding":[80],"policy":[82,149],"that":[83,152,165],"performs":[84],"well":[85],"for":[86],"both":[87],"worst":[89],"case":[90],"and":[91,99,107,122,137,158,170],"dynamics.":[94,183],"Thus,":[95],"define":[97],"robustness":[98,121,157],"consistency":[100],"as":[101],"metrics":[102],"optimizes":[106],"family":[110],"optimization":[112],"problems":[113,175],"whose":[114],"solutions":[115,133],"are":[116,134],"Pareto-optimal":[117,143],"consistency.":[123,159],"Under":[124],"standard":[125],"assumptions":[126],"set,":[130],"optimal":[132],"deterministic,":[135],"Markovian,":[136],"stationary.":[138],"Given":[139],"set":[141],"policies,":[144],"then":[146],"provide":[147,162],"selection":[150],"algorithm":[151,167],"achieves":[153,168],"max-min":[154],"optimality":[155],"across":[156],"Finally,":[160],"empirical":[163],"evidence":[164],"robust":[169],"consistent":[171],"performance":[172],"planning":[174],"even":[176],"under":[177],"significant":[178],"underlying":[182]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-14T00:00:00"}