{"id":"https://openalex.org/W2978426310","doi":"https://doi.org/10.1109/ijcnn.2019.8852019","title":"Strategy Selection in Complex Game Environments Based on Transfer Reinforcement Learning","display_name":"Strategy Selection in Complex Game Environments Based on Transfer Reinforcement Learning","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2978426310","doi":"https://doi.org/10.1109/ijcnn.2019.8852019","mag":"2978426310"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8852019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5091010251","display_name":"Hongwei Ge","orcid":"https://orcid.org/0000-0002-8937-1515"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongwei Ge","raw_affiliation_strings":["College of Computer Science and Technology, Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083343995","display_name":"Mingde Zhao","orcid":"https://orcid.org/0000-0002-6687-8153"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mingde Zhao","raw_affiliation_strings":["School of Computer Science, McGill University, Montr\u00e9al, Canada"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, McGill University, Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323930","display_name":"Kai Zhang","orcid":"https://orcid.org/0000-0002-0093-3690"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021834892","display_name":"Liang Sun","orcid":"https://orcid.org/0000-0003-2794-8654"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Sun","raw_affiliation_strings":["College of Computer Science and Technology, Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091010251"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11712873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.978600025177002,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9775000214576721,"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":0.7973340749740601},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7221586108207703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5603137612342834},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5575465559959412},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.542172372341156},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4886346459388733},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.48441794514656067},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4775072932243347},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4520443081855774},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.4358431398868561},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.4148048758506775},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4114348292350769},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.2008759081363678},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09667864441871643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973340749740601},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7221586108207703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5603137612342834},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5575465559959412},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.542172372341156},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4886346459388733},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.48441794514656067},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4775072932243347},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4520443081855774},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4358431398868561},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.4148048758506775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4114348292350769},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2008759081363678},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09667864441871643},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2019.8852019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1821462560","https://openalex.org/W1949804828","https://openalex.org/W2097113539","https://openalex.org/W2097381042","https://openalex.org/W2107726111","https://openalex.org/W2117341272","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2162768030","https://openalex.org/W2165150801","https://openalex.org/W2165698076","https://openalex.org/W2174786457","https://openalex.org/W2257979135","https://openalex.org/W2426267443","https://openalex.org/W2533806771","https://openalex.org/W2586101872","https://openalex.org/W2596367596","https://openalex.org/W2607014226","https://openalex.org/W2949369413","https://openalex.org/W2950872548","https://openalex.org/W2963911037","https://openalex.org/W2964043796","https://openalex.org/W3022194887","https://openalex.org/W4298857966","https://openalex.org/W4302570325","https://openalex.org/W4319988532","https://openalex.org/W6637967152","https://openalex.org/W6638444622","https://openalex.org/W6638523607","https://openalex.org/W6677347465","https://openalex.org/W6684100231","https://openalex.org/W6684205842","https://openalex.org/W6692846177","https://openalex.org/W6729556111","https://openalex.org/W6735641298","https://openalex.org/W6849896277"],"related_works":["https://openalex.org/W2024736176","https://openalex.org/W4390735358","https://openalex.org/W2948333011","https://openalex.org/W4386619269","https://openalex.org/W1942758450","https://openalex.org/W2994972936","https://openalex.org/W2922338626","https://openalex.org/W4303645333","https://openalex.org/W4312745891","https://openalex.org/W3088045114"],"abstract_inverted_index":{"Boosting":[0],"the":[1,5,46,78,94,98,103,107,114,119,128,132,135,145,153,157,162,166,170,173],"learning":[2,36,62],"process":[3],"in":[4,20,97,106,179],"new":[6,108],"task":[7,19,71,138],"by":[8],"making":[9],"use":[10],"of":[11,23,48,80,172],"previously":[12],"obtained":[13],"knowledge":[14,39,49,68,96,105,121,151],"has":[15],"been":[16],"a":[17,33,53,57,73,85],"challenging":[18],"many":[21],"fields":[22],"industrial":[24],"engineering":[25],"and":[26,41,60,102],"scientific.":[27],"In":[28,45,77],"this":[29],"paper,":[30],"we":[31],"propose":[32],"transfer":[34,150],"reinforcement":[35],"model":[37,54,123,148],"with":[38,165],"Inheritance":[40],"decision-making":[42,81,146],"Assistance":[43],"(trIA).":[44],"stage":[47,79],"inheritance,":[50],"trIA":[51,83,175],"adopts":[52,84],"that":[55,118,144],"employs":[56],"simultaneous":[58],"multi-task":[59,75,100],"multi-instance":[61],"strategy":[63,177],"to":[64,91,156],"compress":[65],"acquired":[66,104],"experts":[67,133],"from":[69,152],"distinct":[70,136],"into":[72],"global":[74,99],"agent.":[76],"assistance,":[82],"dual-column":[86],"progressive":[87],"neural":[88],"network":[89],"framework":[90],"fully":[92],"utilize":[93],"previous":[95],"agent":[101],"task.":[109],"The":[110,140],"experimental":[111],"results":[112,141,164],"on":[113,134],"Atari":[115],"domain":[116],"demonstrate":[117,143],"proposed":[120,174],"inheritance":[122],"can":[124,149],"performed":[125],"at":[126],"nearly":[127],"same":[129],"level":[130],"as":[131],"source":[137,154],"environments.":[139,182],"also":[142],"assistance":[147],"tasks":[155,159],"target":[158],"effectively.":[160],"Moreover,":[161],"comparative":[163],"state-ofthe-art":[167],"algorithms":[168],"validate":[169],"effectiveness":[171],"for":[176],"selection":[178],"complex":[180],"game":[181]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}