{"id":"https://openalex.org/W2789543555","doi":"https://doi.org/10.1109/tnnls.2018.2803729","title":"Reusable Reinforcement Learning via Shallow Trails","display_name":"Reusable Reinforcement Learning via Shallow Trails","publication_year":2018,"publication_date":"2018-03-06","ids":{"openalex":"https://openalex.org/W2789543555","doi":"https://doi.org/10.1109/tnnls.2018.2803729","mag":"2789543555","pmid":"https://pubmed.ncbi.nlm.nih.gov/29771672"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2018.2803729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2018.2803729","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100342263","display_name":"Yang Yu","orcid":"https://orcid.org/0000-0002-1732-9545"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yu","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-1732-9545","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023412620","display_name":"Shi-Yong Chen","orcid":"https://orcid.org/0000-0002-6417-1912"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi-Yong Chen","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-6417-1912","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070849903","display_name":"Qing Da","orcid":"https://orcid.org/0000-0003-2200-0098"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Da","raw_affiliation_strings":["Alibaba Group, Hangzhou, China","National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100621138","display_name":"Zhi\u2010Hua Zhou","orcid":"https://orcid.org/0000-0003-0746-1494"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi-Hua Zhou","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-0746-1494","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":1.853,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88558036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"29","issue":"6","first_page":"2204","last_page":"2215"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9958999752998352,"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":0.9940000176429749,"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":0.8145625591278076},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7964067459106445},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7668491005897522},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6687526702880859},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5459796190261841},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4984428882598877},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4659508168697357},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46121251583099365},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.44240617752075195},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.43180084228515625},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3579023480415344},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1141510009765625},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11145776510238647},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08105123043060303}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8145625591278076},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7964067459106445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7668491005897522},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6687526702880859},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5459796190261841},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4984428882598877},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4659508168697357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46121251583099365},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.44240617752075195},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.43180084228515625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3579023480415344},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1141510009765625},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11145776510238647},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08105123043060303},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2018.2803729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2018.2803729","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:29771672","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29771672","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1518273563","display_name":null,"funder_award_id":"BK20170013","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G697213553","display_name":null,"funder_award_id":"61751306","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"},{"id":"https://openalex.org/F4320322300","display_name":"Jilin University","ror":"https://ror.org/00js3aw79"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324852","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1629143244","https://openalex.org/W1771410628","https://openalex.org/W1938632290","https://openalex.org/W1969074599","https://openalex.org/W2031727428","https://openalex.org/W2083620785","https://openalex.org/W2097381042","https://openalex.org/W2110292307","https://openalex.org/W2112036188","https://openalex.org/W2114235770","https://openalex.org/W2119717200","https://openalex.org/W2125922627","https://openalex.org/W2132057084","https://openalex.org/W2133120480","https://openalex.org/W2133853511","https://openalex.org/W2134197408","https://openalex.org/W2142502798","https://openalex.org/W2144446635","https://openalex.org/W2145339207","https://openalex.org/W2146192612","https://openalex.org/W2155027007","https://openalex.org/W2158782408","https://openalex.org/W2165698076","https://openalex.org/W2166798247","https://openalex.org/W2257979135","https://openalex.org/W2296402458","https://openalex.org/W2342662072","https://openalex.org/W2412094331","https://openalex.org/W2573774999","https://openalex.org/W2585821313","https://openalex.org/W2604877292","https://openalex.org/W2746791238","https://openalex.org/W2911964244","https://openalex.org/W2949634144","https://openalex.org/W2952629144","https://openalex.org/W3101442004","https://openalex.org/W4214717370","https://openalex.org/W4238893454","https://openalex.org/W4293534691","https://openalex.org/W4298174377","https://openalex.org/W4299518610","https://openalex.org/W6636559424","https://openalex.org/W6638018090","https://openalex.org/W6674600207","https://openalex.org/W6677184444","https://openalex.org/W6680171673","https://openalex.org/W6680972505","https://openalex.org/W6682132143","https://openalex.org/W6683204974","https://openalex.org/W6684359289","https://openalex.org/W6684363390","https://openalex.org/W6685726866","https://openalex.org/W6704571135","https://openalex.org/W6728925229","https://openalex.org/W6730027589","https://openalex.org/W6732081638","https://openalex.org/W6735517717","https://openalex.org/W6837117956","https://openalex.org/W6966558720"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,8],"has":[2],"shown":[3],"great":[4],"success":[5],"in":[6,17,76,85,112,119],"helping":[7],"agents":[9],"accomplish":[10,25],"tasks":[11,51,79,102,201],"autonomously":[12],"from":[13,55,80],"environment":[14],"interactions.":[15],"Meanwhile":[16],"many":[18],"real-world":[19],"applications,":[20],"an":[21,40,56],"agent":[22,41],"needs":[23],"to":[24,92,100,114,124,129],"not":[26],"only":[27],"a":[28,33,44,47,131,158,162],"fixed":[29],"task":[30,126,159,181,194],"but":[31],"also":[32,191],"range":[34],"of":[35,49,169,187],"tasks.":[36,177,215],"For":[37],"this":[38,137],"goal,":[39],"can":[42,72,133,205],"learn":[43],"metapolicy":[45,71,132],"over":[46,65],"set":[48],"training":[50,68],"that":[52,103,146,203],"are":[53,104,183],"drawn":[54],"underlying":[57],"distribution.":[58,83],"By":[59],"maximizing":[60],"the":[61,67,70,81,120,141,148,153,167,170,180,185,188],"total":[62],"reward":[63,212],"summed":[64],"all":[66],"tasks,":[69],"then":[73],"be":[74,134],"reused":[75],"accomplishing":[77],"test":[78,214],"same":[82],"However,":[84],"practice,":[86],"we":[87,139],"face":[88],"two":[89,149],"major":[90],"obstacles":[91],"train":[93,206],"and":[94,209],"reuse":[95],"metapolicies":[96,207],"well.":[97],"First,":[98],"how":[99,123],"identify":[101],"unrelated":[105],"or":[106],"even":[107],"opposite":[108],"with":[109],"each":[110],"other,":[111],"order":[113],"avoid":[115],"their":[116],"mutual":[117],"interference":[118],"training.":[121],"Second,":[122],"characterize":[125],"features,":[127],"according":[128],"which":[130],"reused.":[135],"In":[136],"paper,":[138],"propose":[140],"MetA-Policy":[142],"LEarning":[143],"(MAPLE)":[144],"approach":[145],"overcomes":[147],"difficulties":[150],"by":[151,160],"introducing":[152],"shallow":[154,171,189],"trail.":[155],"It":[156],"probes":[157],"running":[161],"roughly":[163],"trained":[164],"policy.":[165],"Using":[166],"rewards":[168,186],"trail,":[172],"MAPLE":[173,204],"automatically":[174],"groups":[175],"similar":[176],"Moreover,":[178],"when":[179],"parameters":[182],"unknown,":[184],"trail":[190],"serve":[192],"as":[193],"features.":[195],"Empirical":[196],"studies":[197],"on":[198,213],"several":[199],"controlling":[200],"verify":[202],"well":[208],"receives":[210],"high":[211]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}