{"id":"https://openalex.org/W2965889088","doi":"https://doi.org/10.1609/aaai.v33i01.33019876","title":"A Theory of State Abstraction for Reinforcement Learning","display_name":"A Theory of State Abstraction for Reinforcement Learning","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2965889088","doi":"https://doi.org/10.1609/aaai.v33i01.33019876","mag":"2965889088"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33019876","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019876","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5075/4948","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5075/4948","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080191195","display_name":"David Abel","orcid":"https://orcid.org/0000-0001-6311-9007"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Abel","raw_affiliation_strings":["Brown University"],"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5080191195"],"corresponding_institution_ids":["https://openalex.org/I175594653"],"apc_list":null,"apc_paid":null,"fwci":1.1807,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.84113111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"33","issue":"01","first_page":"9876","last_page":"9877"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9957000017166138,"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":0.9957000017166138,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9782000184059143,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9470000267028809,"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/abstraction","display_name":"Abstraction","score":0.9269688129425049},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7794636487960815},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7484625577926636},{"id":"https://openalex.org/keywords/abstraction-model-checking","display_name":"Abstraction model checking","score":0.587242841720581},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5173008441925049},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5163601636886597},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4585019052028656},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4409499764442444},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.41984283924102783},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.4180390238761902},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35153496265411377},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.29305267333984375},{"id":"https://openalex.org/keywords/model-checking","display_name":"Model checking","score":0.2606683671474457},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.14510151743888855}],"concepts":[{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.9269688129425049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7794636487960815},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7484625577926636},{"id":"https://openalex.org/C30888246","wikidata":"https://www.wikidata.org/wiki/Q4669969","display_name":"Abstraction model checking","level":3,"score":0.587242841720581},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5173008441925049},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5163601636886597},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4585019052028656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4409499764442444},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41984283924102783},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.4180390238761902},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35153496265411377},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.29305267333984375},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.2606683671474457},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.14510151743888855},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v33i01.33019876","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019876","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5075/4948","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33019876","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019876","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5075/4948","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965889088.pdf","grobid_xml":"https://content.openalex.org/works/W2965889088.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1583380718","https://openalex.org/W1686946872","https://openalex.org/W1754881896","https://openalex.org/W1995875735","https://openalex.org/W2058735307","https://openalex.org/W2089561656","https://openalex.org/W2101167844","https://openalex.org/W2125510930","https://openalex.org/W2149148771","https://openalex.org/W2397240726","https://openalex.org/W2468354762","https://openalex.org/W2803178532","https://openalex.org/W2904715276","https://openalex.org/W2993383518","https://openalex.org/W6637108112","https://openalex.org/W6648982606","https://openalex.org/W6678900246","https://openalex.org/W6712173889"],"related_works":["https://openalex.org/W278680301","https://openalex.org/W2077408436","https://openalex.org/W2144996318","https://openalex.org/W2003959877","https://openalex.org/W2106098610","https://openalex.org/W2020735442","https://openalex.org/W1991474412","https://openalex.org/W1671661949","https://openalex.org/W2151629759","https://openalex.org/W2348940122"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"presents":[2],"a":[3,29,83,97,111],"challenging":[4],"problem:":[5],"agents":[6,43],"must":[7],"generalize":[8],"experiences,":[9],"efficiently":[10],"explore":[11],"the":[12,66,75,141,173],"world,":[13],"and":[14,21,52,60,103,134,137,165],"learn":[15],"from":[16],"feedback":[17],"that":[18,109,125,171],"is":[19,34,72],"delayed":[20],"often":[22],"sparse,":[23],"all":[24,37],"while":[25],"making":[26,57],"use":[27],"of":[28,38,48,68,106,155,163],"limited":[30],"computational":[31],"budget.":[32],"Abstraction":[33],"essential":[35],"to":[36,73,100,146,158,168],"these":[39,116,156],"endeavors.":[40],"Through":[41],"abstraction,":[42,164],"can":[44,126,139],"form":[45],"concise":[46],"models":[47],"both":[49],"their":[50],"surroundings":[51],"behavior,":[53,130],"supporting":[54],"effective":[55,148],"decision":[56],"in":[58,79],"diverse":[59],"complex":[61],"environments.":[62],"To":[63],"this":[64],"end,":[65],"goal":[67],"my":[69],"doctoral":[70],"research":[71],"characterize":[74],"role":[76],"abstraction":[77,99,170],"plays":[78],"reinforcement":[80],"learning,":[81],"with":[82],"focus":[84],"on":[85],"state":[86,98,107,123],"abstraction.":[87],"I":[88,119,150],"offer":[89],"three":[90],"desiderata":[91],"articulating":[92],"what":[93],"it":[94],"means":[95],"for":[96,122],"be":[101,132],"useful,":[102],"introduce":[104],"classes":[105],"abstractions":[108,124],"provide":[110],"partial":[112],"path":[113],"toward":[114],"satisfying":[115],"desiderata.":[117],"Collectively,":[118],"develop":[120],"theory":[121],"1)":[127],"preserve":[128],"near-optimal":[129],"2)":[131],"learned":[133],"computed":[135],"efficiently,":[136],"3)":[138],"lower":[140],"time":[142],"or":[143],"data":[144],"needed":[145],"make":[147],"decisions.":[149],"close":[151],"by":[152],"discussing":[153],"extensions":[154],"results":[157],"an":[159,166],"information":[160],"theoretic":[161],"paradigm":[162],"extension":[167],"hierarchical":[169],"enjoys":[172],"same":[174],"desirable":[175],"properties.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}