{"id":"https://openalex.org/W2783713881","doi":"https://doi.org/10.1109/coase.2017.8256303","title":"Complexity analysis of reinforcement learning and its application to robotics","display_name":"Complexity analysis of reinforcement learning and its application to robotics","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2783713881","doi":"https://doi.org/10.1109/coase.2017.8256303","mag":"2783713881"},"language":"en","primary_location":{"id":"doi:10.1109/coase.2017.8256303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coase.2017.8256303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 13th IEEE Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102812784","display_name":"Bocheng Li","orcid":"https://orcid.org/0009-0001-0675-6445"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bocheng Li","raw_affiliation_strings":["Department of Automation, TNList Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, TNList Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100646502","display_name":"Li Xia","orcid":"https://orcid.org/0000-0002-3193-7336"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Xia","raw_affiliation_strings":["Department of Automation, TNList Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, TNList Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014109600","display_name":"Qianchuan Zhao","orcid":"https://orcid.org/0000-0002-7952-5621"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianchuan Zhao","raw_affiliation_strings":["Department of Automation, TNList Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, TNList Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1425","last_page":"1426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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":0.998199999332428,"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":0.9832000136375427,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9807999730110168,"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":0.9082964062690735},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.707926332950592},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.66911381483078},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.6026335954666138},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5405328273773193},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5203813314437866},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4822588562965393},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3853186368942261},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08565151691436768}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9082964062690735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.707926332950592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.66911381483078},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.6026335954666138},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5405328273773193},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5203813314437866},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4822588562965393},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3853186368942261},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08565151691436768}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/coase.2017.8256303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coase.2017.8256303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 13th IEEE Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2121863487","https://openalex.org/W2146290970","https://openalex.org/W2257979135","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2877093712","https://openalex.org/W2116157560","https://openalex.org/W4310614650","https://openalex.org/W4386738330"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"is":[3],"a":[4],"widely":[5],"adopted":[6],"theory":[7],"in":[8,64],"machine":[9],"learning,":[10],"which":[11],"aims":[12],"to":[13],"handle":[14],"the":[15,23,32,44,55,59],"optimal":[16],"decision":[17],"of":[18,34,46],"intelligent":[19],"agent":[20],"interacting":[21],"with":[22],"stochastic":[24],"dynamic":[25],"environment.":[26],"Its":[27],"origin":[28],"may":[29],"come":[30],"from":[31],"motivation":[33],"phycological":[35],"observations":[36],"since":[37],"1960's":[38],"[1].":[39],"It":[40],"blooms":[41],"recently":[42],"as":[43],"emerging":[45],"large":[47],"sample":[48],"data":[49],"and":[50],"powerful":[51],"computation":[52],"facility,":[53],"especially":[54],"AlphaGo's":[56],"beat":[57],"over":[58],"human":[60],"top":[61],"Go":[62],"player":[63],"2016":[65],"[2].":[66]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}