{"id":"https://openalex.org/W2899685447","doi":"https://doi.org/10.1109/iros.2018.8594201","title":"Regularizing Reinforcement Learning with State Abstraction","display_name":"Regularizing Reinforcement Learning with State Abstraction","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2899685447","doi":"https://doi.org/10.1109/iros.2018.8594201","mag":"2899685447"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2018.8594201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8594201","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":"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/A5075701789","display_name":"Riad Akrour","orcid":"https://orcid.org/0000-0002-8735-6960"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Riad Akrour","raw_affiliation_strings":["CLAS/IAS. TU Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"CLAS/IAS. TU Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013781797","display_name":"Filipe Veiga","orcid":"https://orcid.org/0000-0002-0889-0242"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Filipe Veiga","raw_affiliation_strings":["CLAS/IAS. TU Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"CLAS/IAS. TU Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["CLAS/IAS. TU Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"CLAS/IAS. TU Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110467801","display_name":"Gerhard Neumann","orcid":"https://orcid.org/0000-0002-5483-4225"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Neumann","raw_affiliation_strings":["CLAS/IAS. TU Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"CLAS/IAS. TU Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5075701789"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":2.0283,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.90083911,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"534","last_page":"539"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10524","display_name":"Traffic control and management","score":0.958899974822998,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9526000022888184,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9413986206054688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7171030044555664},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.7087669968605042},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.640678882598877},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5900490283966064},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5820201635360718},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5452916026115417},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5260030031204224},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5033470988273621},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45633500814437866},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4226044714450836},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36064451932907104},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1355063021183014},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12836134433746338},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07224816083908081}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9413986206054688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7171030044555664},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.7087669968605042},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.640678882598877},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5900490283966064},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5820201635360718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5452916026115417},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5260030031204224},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5033470988273621},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45633500814437866},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4226044714450836},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36064451932907104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1355063021183014},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12836134433746338},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07224816083908081},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros.2018.8594201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8594201","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"},{"id":"pmh:oai:pure.mpg.de:item_3049283","is_oa":false,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0003-7E70-2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018)","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.800000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1600813180","https://openalex.org/W1631187438","https://openalex.org/W1754881896","https://openalex.org/W1771410628","https://openalex.org/W1993411524","https://openalex.org/W2073384958","https://openalex.org/W2108535023","https://openalex.org/W2111020392","https://openalex.org/W2123967136","https://openalex.org/W2133853511","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2167590754","https://openalex.org/W2173248099","https://openalex.org/W2256420211","https://openalex.org/W2267881773","https://openalex.org/W2397240726","https://openalex.org/W2402540331","https://openalex.org/W2468354762","https://openalex.org/W2498991332","https://openalex.org/W2600491083","https://openalex.org/W2736601468","https://openalex.org/W2912453235","https://openalex.org/W2962749646","https://openalex.org/W2962803570","https://openalex.org/W2963262099","https://openalex.org/W2963312729","https://openalex.org/W2963615220","https://openalex.org/W2963616477","https://openalex.org/W2963674921","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964227312","https://openalex.org/W3037207827","https://openalex.org/W4211221179","https://openalex.org/W4295549420","https://openalex.org/W4300819200","https://openalex.org/W6635732164","https://openalex.org/W6636614537","https://openalex.org/W6637806891","https://openalex.org/W6638018090","https://openalex.org/W6676557315","https://openalex.org/W6677116005","https://openalex.org/W6678157427","https://openalex.org/W6683204974","https://openalex.org/W6684818487","https://openalex.org/W6684921986","https://openalex.org/W6691861496","https://openalex.org/W6692312642","https://openalex.org/W6692846177","https://openalex.org/W6693502484","https://openalex.org/W6703271639","https://openalex.org/W6712173889","https://openalex.org/W6713151597","https://openalex.org/W6715102896","https://openalex.org/W6719911377","https://openalex.org/W6727349600","https://openalex.org/W6734129231","https://openalex.org/W6735209194","https://openalex.org/W6741002519","https://openalex.org/W6758390756"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W4225571923","https://openalex.org/W2166117066","https://openalex.org/W3212257828","https://openalex.org/W3087814763","https://openalex.org/W2357975469","https://openalex.org/W2999580272","https://openalex.org/W2136202932","https://openalex.org/W4376605461"],"abstract_inverted_index":{"State":[0],"abstraction":[1,32],"in":[2,77],"a":[3,11,44,49,58,90,115,133],"discrete":[4],"reinforcement":[5,36,60,95,128],"learning":[6,37,61,96,129],"setting":[7],"clusters":[8],"states":[9],"sharing":[10],"similar":[12],"optimal":[13,75],"action":[14,35],"to":[15,19,33,66,88],"yield":[16],"an":[17,40],"easier":[18],"solve":[20],"decision":[21],"process.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26,123],"generalize":[27],"the":[28,69,74,84,99,103],"concept":[29],"of":[30,52,83,93,102,136],"state":[31,42,45,70],"continuous":[34],"by":[38,97,131],"defining":[39],"abstract":[41],"as":[43],"cluster":[46],"over":[47],"which":[48],"near-optimal":[50],"policy":[51],"simple":[53],"shape":[54],"exists.":[55],"We":[56,106],"propose":[57],"hierarchical":[59],"algorithm":[62,109],"that":[63,122],"is":[64,87],"able":[65],"simultaneously":[67],"find":[68],"space":[71],"clustering":[72],"and":[73,114,120],"sub-policies":[76],"each":[78],"cluster.":[79],"The":[80],"main":[81],"advantage":[82],"proposed":[85],"framework":[86],"provide":[89],"straightforward":[91],"way":[92],"regularizing":[94],"controlling":[98],"behavioral":[100],"complexity":[101],"learned":[104],"policy.":[105],"apply":[107],"our":[108],"on":[110],"several":[111],"benchmark":[112],"tasks":[113],"robot":[116],"tactile":[117],"manipulation":[118],"task":[119],"show":[121],"can":[124],"match":[125],"state-of-the-art":[126],"deep":[127],"performance":[130],"combining":[132],"small":[134],"number":[135],"linear":[137],"policies.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}