{"id":"https://openalex.org/W2169900954","doi":"https://doi.org/10.1109/adprl.2013.6614999","title":"Delayed insertion and rule effect moderation of domain knowledge for reinforcement learning","display_name":"Delayed insertion and rule effect moderation of domain knowledge for reinforcement learning","publication_year":2013,"publication_date":"2013-04-01","ids":{"openalex":"https://openalex.org/W2169900954","doi":"https://doi.org/10.1109/adprl.2013.6614999","mag":"2169900954"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2013.6614999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2013.6614999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=7654&context=sis_research","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075833644","display_name":"Teck-Hou Teng","orcid":"https://orcid.org/0000-0001-6306-2338"},"institutions":[{"id":"https://openalex.org/I4210150023","display_name":"Computational Intelligence and Information Systems Lab","ror":"https://ror.org/04fqqys39","country_code":"AR","type":"facility","lineage":["https://openalex.org/I4210150023"]}],"countries":["AR"],"is_corresponding":true,"raw_author_name":"Teck-Hou Teng","raw_affiliation_strings":["School of Computer Engineering, Center for Computational Intelligence"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Center for Computational Intelligence","institution_ids":["https://openalex.org/I4210150023"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004167801","display_name":"Ah\u2010Hwee Tan","orcid":"https://orcid.org/0000-0003-0378-4069"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ah-Hwee Tan","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075833644"],"corresponding_institution_ids":["https://openalex.org/I4210150023"],"apc_list":null,"apc_paid":null,"fwci":0.4944,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78130786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"132","last_page":"139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9843000173568726,"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":0.9843000173568726,"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/T10260","display_name":"Software Engineering Research","score":0.9409999847412109,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11675","display_name":"Open Source Software Innovations","score":0.9203000068664551,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/domain-knowledge","display_name":"Domain knowledge","score":0.7595010995864868},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7346885204315186},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5874312520027161},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4958663880825043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.483075886964798},{"id":"https://openalex.org/keywords/moderation","display_name":"Moderation","score":0.46899035573005676},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4438899755477905},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41999754309654236},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08447682857513428}],"concepts":[{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.7595010995864868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7346885204315186},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5874312520027161},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4958663880825043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.483075886964798},{"id":"https://openalex.org/C93225998","wikidata":"https://www.wikidata.org/wiki/Q1941972","display_name":"Moderation","level":2,"score":0.46899035573005676},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4438899755477905},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41999754309654236},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08447682857513428},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/adprl.2013.6614999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2013.6614999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-7654","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=7654&context=sis_research","pdf_url":null,"source":{"id":"https://openalex.org/S4377196871","display_name":"Institutional Knowledge (InK) - Institutional Knowledge at Singapore Management University (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.scopus.com/inward/record.url?eid=2-s2.0-84891554854&partnerID=MN8TOARS","raw_type":"Conference Proceeding Article"}],"best_oa_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-7654","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=7654&context=sis_research","pdf_url":null,"source":{"id":"https://openalex.org/S4377196871","display_name":"Institutional Knowledge (InK) - Institutional Knowledge at Singapore Management University (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.scopus.com/inward/record.url?eid=2-s2.0-84891554854&partnerID=MN8TOARS","raw_type":"Conference Proceeding Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W70755758","https://openalex.org/W163890133","https://openalex.org/W240353860","https://openalex.org/W1587191403","https://openalex.org/W1907447171","https://openalex.org/W1992236203","https://openalex.org/W1992535956","https://openalex.org/W2067203724","https://openalex.org/W2073320424","https://openalex.org/W2104487056","https://openalex.org/W2104895050","https://openalex.org/W2107151099","https://openalex.org/W2135774416","https://openalex.org/W2144219012","https://openalex.org/W2148704197","https://openalex.org/W2149231823","https://openalex.org/W2578350735","https://openalex.org/W6602842217","https://openalex.org/W6606694616","https://openalex.org/W6609174986","https://openalex.org/W6639857337","https://openalex.org/W6675716200","https://openalex.org/W6675798146","https://openalex.org/W6682066797","https://openalex.org/W6732430887"],"related_works":["https://openalex.org/W2740268725","https://openalex.org/W3093710306","https://openalex.org/W750217911","https://openalex.org/W4206949499","https://openalex.org/W2296969234","https://openalex.org/W4226254121","https://openalex.org/W1583422155","https://openalex.org/W1649619740","https://openalex.org/W3213252596","https://openalex.org/W1534006406"],"abstract_inverted_index":{"Though":[0],"not":[1,42,62],"a":[2,123],"fundamental":[3],"pre-requisite":[4],"to":[5,20,34,66,97,108,132,167],"efficient":[6],"machine":[7],"learning,":[8],"insertion":[9,71,100,152,172],"of":[10,49,72,82,92,105,119,136,142,147,153,163,178,187],"domain":[11,29,50,59,73,93,106,120,137,155,179],"knowledge":[12,30,51,60,74,94,107,138,156,180],"into":[13],"adaptive":[14],"virtual":[15],"agent":[16],"is":[17,31,52,165],"nonetheless":[18],"known":[19],"improve":[21],"learning":[22,77],"efficiency":[23],"and":[24,54,78,101,173,185],"reduce":[25,109],"model":[26],"complexity.":[27],"Conventionally,":[28],"inserted":[32],"prior":[33,65],"learning.":[35,67,159,189],"Despite":[36],"being":[37],"effective,":[38],"such":[39,154],"approach":[40],"may":[41,61],"always":[43],"be":[44,56,63],"feasible.":[45],"Firstly,":[46],"the":[47,70,80,90,99,103,110,117,134,171,175,183],"effect":[48,104,112,177],"assumed":[53,176],"can":[55,75,157,181],"inaccurate.":[57],"Also,":[58],"available":[64],"In":[68],"addition,":[69],"frame":[76],"hamper":[79],"discovery":[81],"more":[83],"effective":[84],"knowledge.":[85,121],"Therefore,":[86],"this":[87],"work":[88],"advances":[89],"use":[91,118],"by":[95],"proposing":[96],"delay":[98],"moderate":[102],"framing":[111],"while":[113],"still":[114],"benefiting":[115],"from":[116],"Using":[122],"non-trivial":[124],"pursuit-evasion":[125],"problem":[126],"domain,":[127],"experiments":[128,148,164],"are":[129],"first":[130],"conducted":[131,166],"illustrate":[133,168],"impact":[135,158],"with":[139],"different":[140],"degrees":[141],"truth.":[143],"The":[144,160],"next":[145],"set":[146,162],"illustrates":[149],"how":[150,169],"delayed":[151],"final":[161],"delaying":[170],"moderating":[174],"ensure":[182],"robustness":[184],"versatility":[186],"reinforcement":[188]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}