{"id":"https://openalex.org/W2906852733","doi":"https://doi.org/10.3390/sym11010025","title":"Reusing Source Task Knowledge via Transfer Approximator in Reinforcement Transfer Learning","display_name":"Reusing Source Task Knowledge via Transfer Approximator in Reinforcement Transfer Learning","publication_year":2018,"publication_date":"2018-12-29","ids":{"openalex":"https://openalex.org/W2906852733","doi":"https://doi.org/10.3390/sym11010025","mag":"2906852733"},"language":"en","primary_location":{"id":"doi:10.3390/sym11010025","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym11010025","pdf_url":"https://www.mdpi.com/2073-8994/11/1/25/pdf?version=1546065115","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/11/1/25/pdf?version=1546065115","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101919158","display_name":"Qiao Cheng","orcid":"https://orcid.org/0000-0002-3126-8187"},"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":"Qiao Cheng","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China"],"raw_orcid":"https://orcid.org/0000-0002-3126-8187","affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101985392","display_name":"Xiangke Wang","orcid":"https://orcid.org/0000-0002-5074-7052"},"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":"Xiangke Wang","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107748052","display_name":"Yifeng Niu","orcid":"https://orcid.org/0009-0001-5847-2575"},"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":"Yifeng Niu","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056012647","display_name":"Lincheng Shen","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":"Lincheng Shen","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101919158","https://openalex.org/A5101985392"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":0.6767,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78692486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"11","issue":"1","first_page":"25","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996999979019165,"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":0.996999979019165,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9588000178337097,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9549999833106995,"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/computer-science","display_name":"Computer science","score":0.7962186336517334},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7712063789367676},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.766258955001831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.61931973695755},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6037541031837463},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5946197509765625},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5343379974365234},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.4947068393230438},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.487430602312088},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4842676520347595},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.47205668687820435},{"id":"https://openalex.org/keywords/negative-transfer","display_name":"Negative transfer","score":0.4160221219062805}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7962186336517334},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7712063789367676},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.766258955001831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.61931973695755},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6037541031837463},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5946197509765625},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5343379974365234},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.4947068393230438},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.487430602312088},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4842676520347595},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.47205668687820435},{"id":"https://openalex.org/C2779178101","wikidata":"https://www.wikidata.org/wiki/Q6987274","display_name":"Negative transfer","level":3,"score":0.4160221219062805},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/sym11010025","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym11010025","pdf_url":"https://www.mdpi.com/2073-8994/11/1/25/pdf?version=1546065115","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:06b642ca41b8455fb7013a311b686f51","is_oa":true,"landing_page_url":"https://doaj.org/article/06b642ca41b8455fb7013a311b686f51","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry, Vol 11, Iss 1, p 25 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/sym11010025","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym11010025","pdf_url":"https://www.mdpi.com/2073-8994/11/1/25/pdf?version=1546065115","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G93091113","display_name":null,"funder_award_id":"61403406","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":28,"referenced_works":["https://openalex.org/W1990320219","https://openalex.org/W2020573190","https://openalex.org/W2031727428","https://openalex.org/W2056584142","https://openalex.org/W2097381042","https://openalex.org/W2133040789","https://openalex.org/W2137375617","https://openalex.org/W2169659168","https://openalex.org/W2517639096","https://openalex.org/W2555706138","https://openalex.org/W2562252866","https://openalex.org/W2605369401","https://openalex.org/W2756467676","https://openalex.org/W2789901741","https://openalex.org/W2790162350","https://openalex.org/W2795347172","https://openalex.org/W2802636049","https://openalex.org/W2807652507","https://openalex.org/W2905586244","https://openalex.org/W2962817122","https://openalex.org/W4214717370","https://openalex.org/W6674600207","https://openalex.org/W6676875888","https://openalex.org/W6679818365","https://openalex.org/W6682972110","https://openalex.org/W6705225276","https://openalex.org/W6749625569","https://openalex.org/W6752133560"],"related_works":["https://openalex.org/W2821676139","https://openalex.org/W4382138864","https://openalex.org/W3043695725","https://openalex.org/W4387770285","https://openalex.org/W3022215768","https://openalex.org/W3135975972","https://openalex.org/W3016888008","https://openalex.org/W4387183713","https://openalex.org/W4403518771","https://openalex.org/W2165698076"],"abstract_inverted_index":{"Transfer":[0,38],"Learning":[1,18,39],"(TL)":[2],"has":[3],"received":[4],"a":[5,30,74,99,164],"great":[6],"deal":[7],"of":[8,11,87,94,109,113,120,128,231],"attention":[9],"because":[10],"its":[12],"ability":[13],"to":[14,36,55,92,145,221,228],"speed":[15],"up":[16],"Reinforcement":[17],"(RL)":[19],"by":[20],"reusing":[21],"learned":[22],"knowledge":[23,59,72,107,166],"from":[24,60,153],"other":[25,212],"tasks.":[26],"This":[27],"paper":[28],"proposes":[29],"new":[31],"transfer":[32,53,56,82,155,161,183,207,213],"learning":[33,208,214],"framework,":[34],"referred":[35],"as":[37,117],"via":[40],"Artificial":[41,49],"Neural":[42,50],"Network":[43,51],"Approximator":[44],"(TL-ANNA).":[45],"It":[46],"builds":[47,163],"an":[48],"(ANN)":[52],"approximator":[54,83,162,184],"the":[57,61,65,70,81,85,88,95,105,110,114,118,121,126,129,132,136,142,147,150,154,160,169,173,182,198,205,229,236,239,248,251],"related":[58,106],"source":[62,96,115,174,232],"task":[63,67,90,97,116,134,171,202],"into":[64],"target":[66,89,133,139,170],"and":[68,103,172,191,219,224,259],"reuses":[69],"transferred":[71],"with":[73,98,135,149,238,250,256],"Probabilistic":[75],"Policy":[76],"Reuse":[77],"(PPR)":[78],"scheme.":[79],"Specifically,":[80],"maps":[84],"state":[86],"symmetrically":[91],"states":[93],"certain":[100],"mapping":[101,179,241,253],"rule,":[102,254],"activates":[104],"(components":[108],"action-value":[111],"function)":[112],"input":[119],"ANNs;":[122],"it":[123],"then":[124],"predicts":[125],"quality":[127,230],"actions":[130],"in":[131,216],"ANNs.":[137],"The":[138],"learner":[140],"uses":[141],"PPR":[143],"scheme":[144],"bias":[146],"RL":[148],"suggested":[151],"action":[152],"approximator.":[156],"In":[157,176,234],"this":[158],"way,":[159],"symmetric":[165],"path":[167],"between":[168],"task.":[175],"addition,":[177,235],"two":[178,211],"rules":[180],"for":[181],"are":[185,225],"designed,":[186],"namely,":[187],"Full":[188],"Mapping":[189,193],"Rule":[190],"Group":[192],"Rule.":[194],"Experiments":[195],"performed":[196],"on":[197],"RoboCup":[199],"soccer":[200],"Keepaway":[201],"verified":[203],"that":[204],"proposed":[206],"methods":[209,215],"outperform":[210],"both":[217],"jumpstart":[218],"time":[220],"threshold":[222],"metrics":[223],"more":[226],"robust":[227],"knowledge.":[233],"TL-ANNA":[237],"group":[240],"rule":[242],"exhibits":[243],"slightly":[244],"worse":[245],"performance":[246],"than":[247],"one":[249],"full":[252],"but":[255],"less":[257],"computation":[258],"space":[260],"cost":[261],"when":[262],"appropriate":[263],"grouping":[264],"method":[265],"is":[266],"used.":[267]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}