{"id":"https://openalex.org/W2160808139","doi":"https://doi.org/10.1145/1015330.1015355","title":"Dynamic abstraction in reinforcement learning via clustering","display_name":"Dynamic abstraction in reinforcement learning via clustering","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2160808139","doi":"https://doi.org/10.1145/1015330.1015355","mag":"2160808139"},"language":"en","primary_location":{"id":"doi:10.1145/1015330.1015355","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1015330.1015355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Twenty-first international conference on Machine learning - ICML '04","raw_type":"proceedings-article"},"type":"conference-abstract","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/A5036260775","display_name":"Shie Mannor","orcid":"https://orcid.org/0000-0003-4439-7647"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shie Mannor","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032872922","display_name":"Ishai Menache","orcid":"https://orcid.org/0000-0002-2540-236X"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ishai Menache","raw_affiliation_strings":["Technion, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008313762","display_name":"Amit Hoze","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Amit Hoze","raw_affiliation_strings":["Technion, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028569315","display_name":"Uri Klein","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Uri Klein","raw_affiliation_strings":["Technion, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion, Israel","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":193,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"71"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.994700014591217,"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":0.994700014591217,"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/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.9678000211715698,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9614999890327454,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8078646659851074},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7066127061843872},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6688582897186279},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5977587699890137},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.5413275957107544},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5261083245277405},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4978952407836914},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.4419916868209839},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4330226480960846},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4310223162174225},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40261322259902954},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16946038603782654}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8078646659851074},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7066127061843872},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6688582897186279},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5977587699890137},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5413275957107544},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5261083245277405},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4978952407836914},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.4419916868209839},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4330226480960846},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4310223162174225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40261322259902954},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16946038603782654},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1015330.1015355","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1015330.1015355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Twenty-first international conference on Machine learning - ICML '04","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.5975","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.5975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aicml.cs.ualberta.ca/banff04/icml/pages/papers/104.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.6200000047683716}],"awards":[],"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":20,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1536990779","https://openalex.org/W1540462738","https://openalex.org/W1560495008","https://openalex.org/W1576452626","https://openalex.org/W1592847719","https://openalex.org/W1914583973","https://openalex.org/W1971784203","https://openalex.org/W1990313671","https://openalex.org/W1992419399","https://openalex.org/W2091565802","https://openalex.org/W2109910161","https://openalex.org/W2115502112","https://openalex.org/W2118587067","https://openalex.org/W2121517924","https://openalex.org/W2141559645","https://openalex.org/W2143435603","https://openalex.org/W2160371091","https://openalex.org/W2343637401","https://openalex.org/W3103182070"],"related_works":["https://openalex.org/W2030816003","https://openalex.org/W4239992647","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W3009457412","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W273478400"],"abstract_inverted_index":{"We":[0,81],"consider":[1,87],"a":[2,12,67,89],"graph":[3],"theoretic":[4],"approach":[5],"for":[6,50,76],"automatic":[7],"construction":[8],"of":[9,17,31,55,69,95,98,101],"options":[10,70,73],"in":[11,66,122],"dynamic":[13],"environment.":[14],"A":[15,35],"map":[16,90],"the":[18,24,28,32,43,52,56,64,78,83,96,102,106,123],"environment":[19],"is":[20,38,109],"generated":[21],"on-line":[22],"by":[23],"learning":[25,125],"agent,":[26],"representing":[27],"topological":[29],"structure":[30],"state":[33,44,103],"transitions.":[34],"clustering":[36],"algorithm":[37,85],"then":[39],"used":[40,75],"to":[41,46,63],"partition":[42],"space":[45,57],"different":[47,53],"regions.":[48],"Policies":[49],"reaching":[51],"parts":[54],"are":[58,74],"separately":[59],"learned":[60],"and":[61,86,111],"added":[62],"model":[65],"form":[68],"(macro-actions).":[71],"The":[72],"accelerating":[77],"Q-Learning":[79],"algorithm.":[80],"extend":[82],"basic":[84],"building":[88],"that":[91],"includes":[92],"preliminary":[93],"indication":[94],"location":[97],"\"interesting\"":[99],"regions":[100],"space,":[104],"where":[105],"value":[107],"gradient":[108],"significant":[110,119],"additional":[112],"exploration":[113],"might":[114],"be":[115],"beneficial.":[116],"Experiments":[117],"indicate":[118],"speedups,":[120],"especially":[121],"initial":[124],"phase.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":9}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}