{"id":"https://openalex.org/W2908370668","doi":"https://doi.org/10.1109/iros.2018.8594383","title":"Solving Markov Decision Processes with Reachability Characterization from Mean First Passage Times","display_name":"Solving Markov Decision Processes with Reachability Characterization from Mean First Passage Times","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2908370668","doi":"https://doi.org/10.1109/iros.2018.8594383","mag":"2908370668"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2018.8594383","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8594383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5006168104","display_name":"Shoubhik Debnath","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shoubhik Debnath","raw_affiliation_strings":["Shoubhik Debnath is with NVIDIA Corporation, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shoubhik Debnath is with NVIDIA Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101917996","display_name":"Lantao Liu","orcid":"https://orcid.org/0000-0002-6796-6817"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lantao Liu","raw_affiliation_strings":["Intelligent Systems Engineering Department, Indiana University, Bloomington, Bloomington, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Systems Engineering Department, Indiana University, Bloomington, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077367921","display_name":"Gaurav S. Sukhatme","orcid":"https://orcid.org/0000-0003-2408-474X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav Sukhatme","raw_affiliation_strings":["Department of Computer Science, The University of Southern, California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Southern, California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":null,"first_page":"7063","last_page":"7070"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"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":0.9977999925613403,"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/T10142","display_name":"Formal Methods in Verification","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.9833999872207642,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reachability","display_name":"Reachability","score":0.9219955205917358},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6942896842956543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.673600435256958},{"id":"https://openalex.org/keywords/first-hitting-time-model","display_name":"First-hitting-time model","score":0.6680155992507935},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6235870718955994},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4967709183692932},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.47957414388656616},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4591479003429413},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.4510688781738281},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.44857630133628845},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4416114091873169},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.42754095792770386},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41752704977989197},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29285889863967896},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.2381153404712677},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13423943519592285}],"concepts":[{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.9219955205917358},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6942896842956543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.673600435256958},{"id":"https://openalex.org/C186659197","wikidata":"https://www.wikidata.org/wiki/Q5452195","display_name":"First-hitting-time model","level":2,"score":0.6680155992507935},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6235870718955994},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4967709183692932},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.47957414388656616},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4591479003429413},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.4510688781738281},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.44857630133628845},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4416114091873169},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.42754095792770386},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41752704977989197},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29285889863967896},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2381153404712677},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13423943519592285},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2018.8594383","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8594383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"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":29,"referenced_works":["https://openalex.org/W108082272","https://openalex.org/W169931978","https://openalex.org/W1491843047","https://openalex.org/W1545148916","https://openalex.org/W1626155273","https://openalex.org/W1978942630","https://openalex.org/W1981745143","https://openalex.org/W1997477668","https://openalex.org/W2009533501","https://openalex.org/W2028145673","https://openalex.org/W2048226872","https://openalex.org/W2061504687","https://openalex.org/W2089561656","https://openalex.org/W2119567691","https://openalex.org/W2121733891","https://openalex.org/W2159420891","https://openalex.org/W2313532661","https://openalex.org/W2321292752","https://openalex.org/W2397240726","https://openalex.org/W2497090499","https://openalex.org/W2737668828","https://openalex.org/W3128263354","https://openalex.org/W4233840023","https://openalex.org/W4245108548","https://openalex.org/W6604443580","https://openalex.org/W6672734911","https://openalex.org/W6677811226","https://openalex.org/W6683452725","https://openalex.org/W6712173889"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W1515117609","https://openalex.org/W4323315247","https://openalex.org/W2294884454","https://openalex.org/W3169161914","https://openalex.org/W4321379664","https://openalex.org/W2211790881"],"abstract_inverted_index":{"A":[0],"new":[1,81,128,166],"mechanism":[2],"for":[3,65],"efficiently":[4],"solving":[5],"the":[6,18,26,37,43,55,107,126,145,160],"Markov":[7],"decision":[8],"processes":[9],"(MDPs)":[10],"is":[11,169],"proposed":[12,127],"in":[13,42,120,148],"this":[14,165],"paper.":[15],"We":[16,46],"introduce":[17],"notion":[19],"of":[20,39,57,150,156,162],"reachability":[21,38,50],"landscape":[22],"where":[23],"we":[24,78,115],"use":[25],"Mean":[27,84,93],"First":[28,85,94],"Passage":[29,86,95],"Time":[30,87,96],"(MFPT)":[31],"as":[32],"a":[33,62,75],"means":[34],"to":[35,172,177],"characterize":[36],"every":[40],"state":[41,44],"space.":[45],"show":[47],"that":[48,102,139],"such":[49,74],"characterization":[51],"very":[52],"well":[53],"assesses":[54],"importance":[56],"states":[58,68],"and":[59,69,92,141,154,174],"thus":[60],"provides":[61],"natural":[63],"basis":[64],"effectively":[66],"prioritizing":[67],"approximating":[70],"policies.":[71],"Built":[72],"on":[73],"novel":[76],"observation,":[77],"design":[79],"two":[80],"algorithms":[82],"-":[83,101],"based":[88,97],"Value":[89],"Iteration":[90,99],"(MFPT-VI)":[91],"Policy":[98],"(MFPT-PI)":[100],"have":[103,116,143],"been":[104],"modified":[105],"from":[106,159],"state-of-the-art":[108,146],"solution":[109,167],"methods.":[110],"To":[111],"validate":[112],"our":[113],"design,":[114],"performed":[117],"numerical":[118],"evaluations":[119],"robotic":[121],"decision-making":[122],"scenarios,":[123],"by":[124],"comparing":[125],"methods":[129],"with":[130],"corresponding":[131],"classic":[132],"baseline":[133],"mechanisms.":[134],"The":[135],"evaluation":[136],"results":[137],"showed":[138],"MFPT-VI":[140],"MFPT-PI":[142],"outperformed":[144],"solutions":[147],"terms":[149],"both":[151],"practical":[152],"runtime":[153],"number":[155],"iterations.":[157],"Aside":[158],"advantage":[161],"fast":[163],"convergence,":[164],"method":[168],"intuitively":[170],"easy":[171],"understand":[173],"practically":[175],"simple":[176],"implement.":[178]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}