{"id":"https://openalex.org/W1968768508","doi":"https://doi.org/10.1145/1015330.1015353","title":"Using relative novelty to identify useful temporal abstractions in reinforcement learning","display_name":"Using relative novelty to identify useful temporal abstractions in reinforcement learning","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W1968768508","doi":"https://doi.org/10.1145/1015330.1015353","mag":"1968768508"},"language":"en","primary_location":{"id":"doi:10.1145/1015330.1015353","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1015330.1015353","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://scholarworks.umass.edu/bitstreams/2084c91b-9cf0-4f09-8b6f-e2c9a3f6329e/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079000862","display_name":"\u00d6zg\u00fcr \u015eim\u015fek","orcid":"https://orcid.org/0000-0001-5449-0437"},"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":true,"raw_author_name":"\u00d6zg\u00fcr \u015eim\u015fek","raw_affiliation_strings":["University of Massachusetts, Amherst, MA","University of Massachusetts, Amherst MA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089808068","display_name":"Andrew G. Barto","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":"Andrew G. Barto","raw_affiliation_strings":["University of Massachusetts, Amherst, MA","University of Massachusetts, Amherst MA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst MA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079000862"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":12.0257,"has_fulltext":true,"cited_by_count":178,"citation_normalized_percentile":{"value":0.98460595,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"95"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9944999814033508,"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":0.96670001745224,"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/novelty","display_name":"Novelty","score":0.9452263116836548},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8979818820953369},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8158979415893555},{"id":"https://openalex.org/keywords/novelty-detection","display_name":"Novelty detection","score":0.6933234930038452},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.6277172565460205},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5949826836585999},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5917298793792725},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47378870844841003},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4561973214149475},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0917046070098877},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08990976214408875}],"concepts":[{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.9452263116836548},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8979818820953369},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8158979415893555},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.6933234930038452},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.6277172565460205},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5949826836585999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5917298793792725},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47378870844841003},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4561973214149475},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0917046070098877},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08990976214408875},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","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":5,"locations":[{"id":"doi:10.1145/1015330.1015353","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1015330.1015353","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:scholarworks.umass.edu:cs_faculty_pubs-1020","is_oa":true,"landing_page_url":"https://scholarworks.umass.edu/cs_faculty_pubs/5","pdf_url":"https://scholarworks.umass.edu/bitstreams/2084c91b-9cf0-4f09-8b6f-e2c9a3f6329e/download","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Department Faculty Publication Series","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.2.4090","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.2.4090","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/102.ps","raw_type":"text"},{"id":"pmh:oai:scholarworks.umass.edu:20.500.14394/10131","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.14394/10131","pdf_url":null,"source":{"id":"https://openalex.org/S4306402057","display_name":"Scholarworks (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"published","raw_type":"Article"},{"id":"pmh:oai:works.bepress.com:andrew_barto-1002","is_oa":false,"landing_page_url":"https://works.bepress.com/andrew_barto/3","pdf_url":null,"source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Andrew G. Barto","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:scholarworks.umass.edu:cs_faculty_pubs-1020","is_oa":true,"landing_page_url":"https://scholarworks.umass.edu/cs_faculty_pubs/5","pdf_url":"https://scholarworks.umass.edu/bitstreams/2084c91b-9cf0-4f09-8b6f-e2c9a3f6329e/download","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Department Faculty Publication Series","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1968768508.pdf","grobid_xml":"https://content.openalex.org/works/W1968768508.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1536990779","https://openalex.org/W1540462738","https://openalex.org/W1568042657","https://openalex.org/W1585861384","https://openalex.org/W1586944634","https://openalex.org/W1598052524","https://openalex.org/W2109910161","https://openalex.org/W2114451917","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2141559645","https://openalex.org/W2143435603","https://openalex.org/W2158548602","https://openalex.org/W2160198238","https://openalex.org/W2295762292","https://openalex.org/W2489939061","https://openalex.org/W2799061466","https://openalex.org/W3023407077","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2064636555","https://openalex.org/W2585503716","https://openalex.org/W1939982668","https://openalex.org/W2105014086","https://openalex.org/W2076090200","https://openalex.org/W4312933423","https://openalex.org/W3025682415","https://openalex.org/W2081173909","https://openalex.org/W4382317424","https://openalex.org/W1532481220"],"abstract_inverted_index":{"We":[0,14,70],"present":[1],"a":[2,25,37,50,54,78],"new":[3],"method":[4,38,76],"for":[5,39],"automatically":[6],"creating":[7],"useful":[8,33],"temporal":[9],"abstractions":[10],"in":[11,77],"reinforcement":[12],"learning.":[13],"argue":[15],"that":[16,18,62],"states":[17],"allow":[19],"the":[20,29,43,64,72,75],"agent":[21,65],"to":[22,24,67],"transition":[23],"different":[26],"region":[27],"of":[28,45,74,80],"state":[30,51],"space":[31],"are":[32],"subgoals,":[34],"and":[35],"propose":[36],"identifying":[40],"them":[41],"using":[42],"concept":[44],"relative":[46],"novelty.":[47],"When":[48],"such":[49],"is":[52,60],"identified,":[53],"temporally-extended":[55],"activity":[56],"(e.g.,":[57],"an":[58],"option)":[59],"generated":[61],"takes":[63],"efficiently":[66],"this":[68],"state.":[69],"illustrate":[71],"utility":[73],"number":[79],"tasks.":[81]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":10}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}