{"id":"https://openalex.org/W1586944634","doi":null,"title":"PolicyBlocks: An Algorithm for Creating Useful Macro-Actions in Reinforcement Learning","display_name":"PolicyBlocks: An Algorithm for Creating Useful Macro-Actions in Reinforcement Learning","publication_year":2002,"publication_date":"2002-07-08","ids":{"openalex":"https://openalex.org/W1586944634","mag":"1586944634"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.19.5587","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.5587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-anw.cs.umass.edu/~pickett/pickettICML2002.ps","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5054302182","display_name":"Marc Pickett","orcid":"https://orcid.org/0009-0003-6493-1269","observed_orcids":["https://orcid.org/0009-0003-6493-1269"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marc Pickett","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089808068","display_name":"Andrew G. Barto","orcid":"https://orcid.org/0000-0002-3581-1896","observed_orcids":["https://orcid.org/0000-0002-3581-1896"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew G. Barto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6951,"has_fulltext":false,"cited_by_count":93,"citation_normalized_percentile":{"value":0.8984857,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"506","last_page":"513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/macro-actions","display_name":"macro-actions","score":0.8349999785423279},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6959999799728394},{"id":"https://openalex.org/keywords/task-generalization","display_name":"task generalization","score":0.5},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.5649999976158142},{"id":"https://openalex.org/keywords/related-tasks","display_name":"related tasks","score":0.4690000116825104},{"id":"https://openalex.org/keywords/accelerated-learning","display_name":"accelerated learning","score":0.6420000195503235}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7922106981277466},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.705548107624054},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.6869363784790039},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4644849896430969},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38017696142196655},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32408392429351807},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1048399806022644}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.19.5587","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.5587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-anw.cs.umass.edu/~pickett/pickettICML2002.ps","raw_type":"text"},{"id":"mag:1586944634","doi":null,"is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/conf/icml/icml2002.html#PickettB02","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1540462738","https://openalex.org/W1585861384","https://openalex.org/W1754881896","https://openalex.org/W2001729196","https://openalex.org/W2039153121","https://openalex.org/W2109910161","https://openalex.org/W2114451917","https://openalex.org/W2121863487","https://openalex.org/W2143435603","https://openalex.org/W2160198238","https://openalex.org/W3011120880","https://openalex.org/W4249889787"],"related_works":["https://openalex.org/W7099271522","https://openalex.org/W7029654074","https://openalex.org/W2912283104","https://openalex.org/W2768663371","https://openalex.org/W3012281279","https://openalex.org/W196647782","https://openalex.org/W2543063639","https://openalex.org/W7096463919","https://openalex.org/W2924136311","https://openalex.org/W2974036326"],"abstract_inverted_index":{"We":[0],"present":[1],"PolicyBlocks,":[2],"an":[3],"algorithm":[4],"by":[5,25],"which":[6],"a":[7,16],"reinforcement":[8],"learning":[9,36],"agent":[10,22],"can":[11],"extract":[12],"useful":[13],"macro-actions":[14],"from":[15],"set":[17],"of":[18],"related":[19,40],"tasks.":[20,32],"The":[21],"creates":[23],"macroactions":[24],"finding":[26],"commonalities":[27],"in":[28],"solutions":[29],"to":[30,37],"previous":[31],"Using":[33],"these":[34],"macro-actions,":[35],"do":[38],"future":[39],"tasks":[41],"is":[42],"accelerated.":[43]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":7}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}