{"id":"https://openalex.org/W4312403453","doi":"https://doi.org/10.1109/iros47612.2022.9981612","title":"Selecting the Partial State Abstractions of MDPs: A Metareasoning Approach with Deep Reinforcement Learning","display_name":"Selecting the Partial State Abstractions of MDPs: A Metareasoning Approach with Deep Reinforcement Learning","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312403453","doi":"https://doi.org/10.1109/iros47612.2022.9981612"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981612","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 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/A5032977536","display_name":"Samer B. Nashed","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samer B. Nashed","raw_affiliation_strings":["University of Massachusetts,Amherst,MA,USA","University of Massachusetts, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts,Amherst,MA,USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080873677","display_name":"Justin Svegliato","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Svegliato","raw_affiliation_strings":["University of California,Berkeley,CA,USA","University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley,CA,USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012627495","display_name":"Abhinav Bhatia","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Bhatia","raw_affiliation_strings":["University of Massachusetts,Amherst,MA,USA","University of Massachusetts, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts,Amherst,MA,USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007305440","display_name":"Stuart Russell","orcid":"https://orcid.org/0000-0001-5252-4306"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stuart Russell","raw_affiliation_strings":["University of California,Berkeley,CA,USA","University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley,CA,USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027224308","display_name":"Shlomo Zilberstein","orcid":"https://orcid.org/0000-0001-9817-7848"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shlomo Zilberstein","raw_affiliation_strings":["University of Massachusetts,Amherst,MA,USA","University of Massachusetts, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts,Amherst,MA,USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11665","last_page":"11670"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.979200005531311,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.979200005531311,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8502480983734131},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.777268648147583},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7680823802947998},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6886064410209656},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6602074503898621},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6323378086090088},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6023780107498169},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5344846248626709},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5236054062843323},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44752490520477295},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4328418970108032},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3853057622909546},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3259311020374298},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3182868957519531},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1245642602443695},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08678919076919556}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8502480983734131},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.777268648147583},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7680823802947998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6886064410209656},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6602074503898621},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6323378086090088},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6023780107498169},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5344846248626709},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5236054062843323},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44752490520477295},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4328418970108032},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3853057622909546},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3259311020374298},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3182868957519531},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1245642602443695},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08678919076919556},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981612","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":0.7900000214576721}],"awards":[{"id":"https://openalex.org/G3890584937","display_name":null,"funder_award_id":"IIS-1813490,IIS-1954782","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W103181800","https://openalex.org/W1538856678","https://openalex.org/W1790709155","https://openalex.org/W1844343792","https://openalex.org/W1963873191","https://openalex.org/W2040827706","https://openalex.org/W2097980248","https://openalex.org/W2159961872","https://openalex.org/W2210091696","https://openalex.org/W2397240726","https://openalex.org/W2522157686","https://openalex.org/W2572919868","https://openalex.org/W2605325129","https://openalex.org/W2774585356","https://openalex.org/W2783462030","https://openalex.org/W2803178532","https://openalex.org/W2807878181","https://openalex.org/W2946767964","https://openalex.org/W3003994825","https://openalex.org/W3090779881","https://openalex.org/W3176598668","https://openalex.org/W3207514672","https://openalex.org/W4312361832","https://openalex.org/W6638739688","https://openalex.org/W6674880867","https://openalex.org/W6687999223","https://openalex.org/W6712173889","https://openalex.org/W6727405266","https://openalex.org/W6731951519","https://openalex.org/W6752255449","https://openalex.org/W6763255703","https://openalex.org/W6797029100"],"related_works":["https://openalex.org/W4388236136","https://openalex.org/W2807018115","https://openalex.org/W4200250224","https://openalex.org/W2285658092","https://openalex.org/W2126560268","https://openalex.org/W187740018","https://openalex.org/W2482498454","https://openalex.org/W2162286586","https://openalex.org/W2947128950","https://openalex.org/W4255368532"],"abstract_inverted_index":{"Markov":[0],"decision":[1],"processes":[2],"(MDPs)":[3],"are":[4],"a":[5,23,49,60,91,142,147],"common":[6],"general-purpose":[7],"model":[8],"used":[9],"in":[10],"robotics":[11,21],"for":[12,26],"representing":[13],"sequential":[14],"decision-making":[15],"problems.":[16],"Given":[17],"the":[18,36,39,44,114,121],"complexity":[19],"of":[20,38,46,93,120],"applications,":[22],"popular":[24],"approach":[25,136,145],"approximately":[27],"solving":[28],"MDPs":[29],"relies":[30],"on":[31,146],"state":[32,40,72],"aggregation":[33],"to":[34,125],"reduce":[35],"size":[37],"space":[41],"but":[42],"at":[43,123],"expense":[45],"policy":[47,52],"fidelity-offering":[48],"trade-off":[50,77],"between":[51],"quality":[53],"and":[54,96,117,141],"computation":[55],"time.":[56],"Naturally,":[57],"this":[58,76,83,87],"poses":[59],"challenging":[61],"metareasoning":[62,88,135],"problem:":[63],"how":[64],"can":[65],"an":[66],"autonomous":[67],"system":[68],"dynamically":[69],"select":[70],"different":[71],"abstractions":[73],"that":[74,112,133],"optimize":[75],"as":[78,127],"it":[79,98],"operates":[80],"online?":[81],"In":[82],"paper,":[84],"we":[85,106,131],"formalize":[86],"problem":[89],"with":[90],"notion":[92],"time-dependent":[94],"utility":[95],"solve":[97],"using":[99],"deep":[100],"reinforcement":[101],"learning.":[102],"To":[103],"do":[104],"this,":[105],"develop":[107],"several":[108,138],"general,":[109],"cheap":[110],"heuristics":[111],"summarize":[113],"reward":[115],"structure":[116],"transition":[118],"topology":[119],"MDP":[122],"hand":[124],"serve":[126],"effective":[128],"features.":[129],"Empirically,":[130],"demonstrate":[132],"our":[134],"outperforms":[137],"baseline":[139],"approaches":[140],"strong":[143],"heuristic":[144],"standard":[148],"benchmark":[149],"domain.":[150]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}