{"id":"https://openalex.org/W2741381403","doi":"https://doi.org/10.24963/ijcai.2017/196","title":"Efficient Reinforcement Learning with Hierarchies of Machines by Leveraging Internal Transitions","display_name":"Efficient Reinforcement Learning with Hierarchies of Machines by Leveraging Internal Transitions","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2741381403","doi":"https://doi.org/10.24963/ijcai.2017/196","mag":"2741381403"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/196","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/196","pdf_url":"https://www.ijcai.org/proceedings/2017/0196.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0196.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083303426","display_name":"Aijun Bai","orcid":"https://orcid.org/0000-0002-5164-4629"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aijun Bai","raw_affiliation_strings":["University of California at Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104083277","display_name":"Stuart Russell","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stuart Russell","raw_affiliation_strings":["University of California at Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8915,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.92928053,"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":"1418","last_page":"1424"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12288","display_name":"Optimization and Search Problems","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9860000014305115,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9338409900665283},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7793190479278564},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7775721549987793},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6469160318374634},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6050043702125549},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5752303600311279},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5622865557670593},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5499604940414429},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.46346890926361084},{"id":"https://openalex.org/keywords/finite-state-machine","display_name":"Finite-state machine","score":0.45525041222572327},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3707016110420227},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16390913724899292},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08476701378822327}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9338409900665283},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7793190479278564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7775721549987793},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6469160318374634},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6050043702125549},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5752303600311279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5622865557670593},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5499604940414429},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.46346890926361084},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.45525041222572327},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3707016110420227},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16390913724899292},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08476701378822327},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2017/196","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/196","pdf_url":"https://www.ijcai.org/proceedings/2017/0196.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/196","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/196","pdf_url":"https://www.ijcai.org/proceedings/2017/0196.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6675157252","display_name":null,"funder_award_id":"N00014-12-1-0609","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G7685818843","display_name":null,"funder_award_id":"N00014-12-1","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2741381403.pdf","grobid_xml":"https://content.openalex.org/works/W2741381403.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1492974543","https://openalex.org/W1977655452","https://openalex.org/W2089561656","https://openalex.org/W2104641222","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2145339207","https://openalex.org/W2145739724","https://openalex.org/W2158548602","https://openalex.org/W2257979135","https://openalex.org/W2493256084","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"In":[0,71],"the":[1,7,67,102,105,109],"context":[2],"of":[3,9,11,24,42,94,104],"hierarchical":[4,25,52,78],"reinforcement":[5,35,79],"learning,":[6],"idea":[8],"hierarchies":[10],"abstract":[12],"machines":[13,28],"(HAMs)":[14],"is":[15],"to":[16,37],"write":[17],"a":[18,22,47,61,76,114],"partial":[19,44],"policy":[20],"as":[21],"set":[23],"finite":[26],"state":[27,69,103],"with":[29,49,66],"unspecified":[30],"choice":[31],"states,":[32],"and":[33,88,113],"use":[34],"learning":[36,80],"learn":[38],"an":[39],"optimal":[40],"completion":[41],"this":[43,72],"policy.":[45],"Given":[46],"HAM":[48],"potentially":[50],"deep":[51],"structure,":[53],"there":[54],"often":[55],"exist":[56],"many":[57],"internal":[58,85],"transitions":[59,86],"where":[60],"machine":[62,65],"calls":[63],"another":[64],"environment":[68],"unchanged.":[70],"paper,":[73],"we":[74],"propose":[75],"new":[77],"algorithm":[81,100],"that":[82],"discovers":[83],"such":[84],"automatically,":[87],"shortcircuits":[89],"them":[90],"recursively":[91],"in":[92],"computation":[93],"Q":[95],"values.":[96],"The":[97],"resulting":[98],"HAMQ-INT":[99],"outperforms":[101],"art":[106],"significantly":[107],"on":[108],"benchmark":[110],"Taxi":[111],"domain":[112],"much":[115],"more":[116],"complex":[117],"RoboCup":[118],"Keepaway":[119],"domain.":[120]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}