{"id":"https://openalex.org/W2774982397","doi":"https://doi.org/10.1145/3167132.3167165","title":"Deep reinforcement learning boosted by external knowledge","display_name":"Deep reinforcement learning boosted by external knowledge","publication_year":2018,"publication_date":"2018-04-09","ids":{"openalex":"https://openalex.org/W2774982397","doi":"https://doi.org/10.1145/3167132.3167165","mag":"2774982397"},"language":"en","primary_location":{"id":"doi:10.1145/3167132.3167165","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3167132.3167165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd Annual ACM Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1712.04101","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Nicolas Bougie","orcid":null},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nicolas Bougie","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ryutaro Ichise","orcid":null},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryutaro Ichise","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":0.7923,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.76733567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"331","last_page":"338"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9894999861717224,"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":0.9879000186920166,"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":0.8349000215530396},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5152999758720398},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45879998803138733},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4490000009536743},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4189999997615814},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4172999858856201},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.412200003862381}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8349000215530396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7160999774932861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6906999945640564},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5152999758720398},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45879998803138733},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4490000009536743},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4230000078678131},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4172999858856201},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.3603000044822693},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2621999979019165}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3167132.3167165","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3167132.3167165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd Annual ACM Symposium on Applied Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1712.04101","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.04101","pdf_url":"https://arxiv.org/pdf/1712.04101","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1712.04101","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.04101","pdf_url":"https://arxiv.org/pdf/1712.04101","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2031489346","https://openalex.org/W2064675550","https://openalex.org/W2963871073","https://openalex.org/W4214717370","https://openalex.org/W4249441547"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"improvements":[1],"in":[2,11,20,39,87],"deep":[3,52],"reinforcement":[4,53,109],"learning":[5,25,54,104,110],"have":[6],"allowed":[7],"to":[8,47,106],"solve":[9],"problems":[10],"many":[12],"2D":[13],"domains":[14],"such":[15],"as":[16],"Atari":[17],"games.":[18],"However,":[19],"complex":[21],"3D":[22,89],"environments,":[23],"numerous":[24],"episodes":[26],"are":[27],"required":[28],"which":[29],"may":[30],"be":[31],"too":[32],"time":[33],"consuming":[34],"or":[35],"even":[36],"impossible":[37],"especially":[38],"real-world":[40],"scenarios.":[41],"We":[42,80],"present":[43],"a":[44,88,107],"new":[45],"architecture":[46],"combine":[48],"external":[49],"knowledge":[50],"and":[51,74,102],"using":[55],"only":[56],"visual":[57],"input.":[58],"A":[59],"key":[60],"concept":[61],"of":[62,78,84],"our":[63,85],"system":[64],"is":[65],"augmenting":[66],"image":[67],"input":[68],"by":[69],"adding":[70],"environment":[71,91],"feature":[72],"information":[73],"combining":[75],"two":[76],"sources":[77],"decision.":[79],"evaluate":[81],"the":[82,93],"performances":[83],"method":[86],"partially-observable":[90],"from":[92],"Microsoft":[94],"Malmo":[95],"platform.":[96],"Experimental":[97],"evaluation":[98],"exhibits":[99],"higher":[100],"performance":[101],"faster":[103],"compared":[105],"single":[108],"model.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2017-12-22T00:00:00"}