{"id":"https://openalex.org/W4226458584","doi":"https://doi.org/10.1142/s1752890922300011","title":"Survey of Reinforcement Learning based on Human Prior Knowledge","display_name":"Survey of Reinforcement Learning based on Human Prior Knowledge","publication_year":2022,"publication_date":"2022-03-01","ids":{"openalex":"https://openalex.org/W4226458584","doi":"https://doi.org/10.1142/s1752890922300011"},"language":"en","primary_location":{"id":"doi:10.1142/s1752890922300011","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1752890922300011","pdf_url":null,"source":{"id":"https://openalex.org/S4210199942","display_name":"Journal of Uncertain Systems","issn_l":"1752-8909","issn":["1752-8909","1752-8917"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Uncertain Systems","raw_type":"journal-article"},"type":"article","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/A5055925624","display_name":"Zijing Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijing Guo","raw_affiliation_strings":["College of Information System and Management, National University of Defense Technology, Changsha 130012, P. R. China"],"affiliations":[{"raw_affiliation_string":"College of Information System and Management, National University of Defense Technology, Changsha 130012, P. R. China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047295323","display_name":"Chendie Yao","orcid":"https://orcid.org/0000-0003-4652-9594"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chendie Yao","raw_affiliation_strings":["College of Information System and Management, National University of Defense Technology, Changsha 130012, P. R. China"],"affiliations":[{"raw_affiliation_string":"College of Information System and Management, National University of Defense Technology, Changsha 130012, P. R. China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081897060","display_name":"Yanghe Feng","orcid":"https://orcid.org/0000-0003-1608-8695"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanghe Feng","raw_affiliation_strings":["College of Information System and Management, National University of Defense Technology, Changsha 130012, P. R. China"],"affiliations":[{"raw_affiliation_string":"College of Information System and Management, National University of Defense Technology, Changsha 130012, P. R. China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100445659","display_name":"Yue Xu","orcid":"https://orcid.org/0000-0002-1137-0272"},"institutions":[{"id":"https://openalex.org/I4210118317","display_name":"81th Hospital of PLA","ror":"https://ror.org/02xxx6w64","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210118317"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Xu","raw_affiliation_strings":["The No. 31102 Troop of PLA, Nanjing, 210016, P. R. China"],"affiliations":[{"raw_affiliation_string":"The No. 31102 Troop of PLA, Nanjing, 210016, P. R. China","institution_ids":["https://openalex.org/I4210118317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081897060"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.6631,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73256915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"15","issue":"01","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T12761","display_name":"Data Stream Mining Techniques","score":0.9057999849319458,"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":0.8793551921844482},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7804993391036987},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.671622633934021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.553024411201477},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5489516854286194},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.48793455958366394},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45530715584754944},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.42907750606536865},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.41988348960876465},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1253901720046997}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8793551921844482},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7804993391036987},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.671622633934021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.553024411201477},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5489516854286194},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.48793455958366394},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45530715584754944},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.42907750606536865},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.41988348960876465},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1253901720046997},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s1752890922300011","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1752890922300011","pdf_url":null,"source":{"id":"https://openalex.org/S4210199942","display_name":"Journal of Uncertain Systems","issn_l":"1752-8909","issn":["1752-8909","1752-8917"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Uncertain Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G2118812850","display_name":null,"funder_award_id":"71701205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2625976379","https://openalex.org/W2837981523","https://openalex.org/W2909507202","https://openalex.org/W2912571273","https://openalex.org/W2996674374","https://openalex.org/W3039772337","https://openalex.org/W3143072515","https://openalex.org/W3184846191","https://openalex.org/W4206475632"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"At":[0],"present,":[1],"task":[2,45],"planning":[3,46,58],"is":[4,32,40,51,105],"mainly":[5],"solved":[6],"by":[7,114],"rules":[8],"or":[9],"operational":[10],"research":[11],"methods.":[12],"The":[13],"time":[14,122],"complexity":[15,18],"and":[16,92,101,156,161],"space":[17],"of":[19,27,60,112,123,141,158],"these":[20],"methods":[21,129],"increase":[22],"exponentially":[23],"with":[24,68,86,135,146],"the":[25,56,69,73,77,84,98,102,120,128,154,159,164,171],"growth":[26],"problem":[28,59,85],"size.":[29],"Thus,":[30,125],"it":[31,39],"challenging":[33],"to":[34,42,54,71,96],"solve":[35,43,55],"large-scale":[36],"problems.":[37,47,124],"Moreover,":[38],"helpless":[41],"dynamic":[44,57],"Reinforcement":[48],"learning":[49,113],"(RL)":[50],"often":[52],"used":[53],"continuous":[61],"decision":[62],"making.":[63],"RL":[64,78,136],"agent":[65],"constantly":[66],"interacts":[67],"environment":[70,160],"achieve":[72],"expected":[74],"goal.":[75],"However,":[76],"method":[79],"meets":[80],"challenges":[81],"when":[82],"handling":[83],"ample":[87],"state":[88],"space.":[89],"More":[90],"sampling":[91,155],"exploration":[93,121,157],"are":[94],"needed":[95],"update":[97],"strategy":[99,166],"gradient,":[100],"convergence":[103],"speed":[104],"slow.":[106],"Humans":[107],"ensure":[108],"a":[109],"quick":[110],"start":[111],"using":[115],"prior":[116,133,143],"knowledge,":[117],"which":[118,130],"reduces":[119],"we":[126,169],"review":[127],"combine":[131],"human":[132,142],"knowledge":[134,144],"through":[137],"temporal":[138],"node":[139],"classification":[140],"combined":[145],"RL.":[147],"In":[148],"this":[149],"way,":[150],"agents":[151],"effectively":[152],"reduce":[153],"eventually":[162],"get":[163],"optimal":[165],"faster.":[167],"Finally,":[168],"propose":[170],"development":[172],"direction.":[173]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}