{"id":"https://openalex.org/W3002873216","doi":"https://doi.org/10.1109/robio49542.2019.8961391","title":"Efficient Robotic Task Generalization Using Deep Model Fusion Reinforcement Learning","display_name":"Efficient Robotic Task Generalization Using Deep Model Fusion Reinforcement Learning","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3002873216","doi":"https://doi.org/10.1109/robio49542.2019.8961391","mag":"3002873216"},"language":"en","primary_location":{"id":"doi:10.1109/robio49542.2019.8961391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio49542.2019.8961391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5002121694","display_name":"Tianying Wang","orcid":"https://orcid.org/0000-0002-2826-5364"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tianying Wang","raw_affiliation_strings":["A*STAR Artificial Intelligence Initiative (A*AI),Singapore,138632","A*STAR Artificial Intelligence Initiative (A*AI), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A*STAR Artificial Intelligence Initiative (A*AI),Singapore,138632","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"A*STAR Artificial Intelligence Initiative (A*AI), Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067846625","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0002-2725-6458"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["A*STAR Artificial Intelligence Initiative (A*AI),Singapore,138632","A*STAR Artificial Intelligence Initiative (A*AI), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A*STAR Artificial Intelligence Initiative (A*AI),Singapore,138632","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"A*STAR Artificial Intelligence Initiative (A*AI), Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011442804","display_name":"Wei Qi Toh","orcid":"https://orcid.org/0000-0002-7375-5012"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Qi Toh","raw_affiliation_strings":["A*STAR Artificial Intelligence Initiative (A*AI),Singapore,138632","A*STAR Artificial Intelligence Initiative (A*AI), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A*STAR Artificial Intelligence Initiative (A*AI),Singapore,138632","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"A*STAR Artificial Intelligence Initiative (A*AI), Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015639955","display_name":"Hongyuan Zhu","orcid":"https://orcid.org/0000-0001-5177-8320"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hongyuan Zhu","raw_affiliation_strings":["A*STAR Artificial Intelligence Initiative (A*AI),Singapore,138632","A*STAR Artificial Intelligence Initiative (A*AI), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A*STAR Artificial Intelligence Initiative (A*AI),Singapore,138632","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"A*STAR Artificial Intelligence Initiative (A*AI), Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073326796","display_name":"Cheston Tan","orcid":"https://orcid.org/0000-0003-1248-4906"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Cheston Tan","raw_affiliation_strings":["A*STAR Artificial Intelligence Initiative (A*AI),Singapore,138632","A*STAR Artificial Intelligence Initiative (A*AI), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A*STAR Artificial Intelligence Initiative (A*AI),Singapore,138632","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"A*STAR Artificial Intelligence Initiative (A*AI), Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017822851","display_name":"Yan Wu","orcid":"https://orcid.org/0000-0002-4644-0664"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yan Wu","raw_affiliation_strings":["A*STAR Artificial Intelligence Initiative (A*AI),Singapore,138632","A*STAR Artificial Intelligence Initiative (A*AI), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A*STAR Artificial Intelligence Initiative (A*AI),Singapore,138632","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"A*STAR Artificial Intelligence Initiative (A*AI), Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102013358","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0003-4098-2339"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["A*STAR Artificial Intelligence Initiative (A*AI),Singapore,138632","A*STAR Artificial Intelligence Initiative (A*AI), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A*STAR Artificial Intelligence Initiative (A*AI),Singapore,138632","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"A*STAR Artificial Intelligence Initiative (A*AI), Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103244741","display_name":"Wei Jing","orcid":"https://orcid.org/0000-0003-3286-5925"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Jing","raw_affiliation_strings":["A*STAR Artificial Intelligence Initiative (A*AI),Singapore,138632","A*STAR Artificial Intelligence Initiative (A*AI), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A*STAR Artificial Intelligence Initiative (A*AI),Singapore,138632","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"A*STAR Artificial Intelligence Initiative (A*AI), Singapore","institution_ids":["https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I115228651"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"148","last_page":"153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9860000014305115,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7995097637176514},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7827481031417847},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7726719379425049},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7495400905609131},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7059489488601685},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6569409370422363},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5433304309844971},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4380030930042267},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4314332902431488},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4312555193901062},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.41047078371047974},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10102349519729614},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06373125314712524}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7995097637176514},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7827481031417847},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7726719379425049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7495400905609131},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7059489488601685},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6569409370422363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5433304309844971},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4380030930042267},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4314332902431488},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4312555193901062},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.41047078371047974},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10102349519729614},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06373125314712524},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio49542.2019.8961391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio49542.2019.8961391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1977655452","https://openalex.org/W2096001037","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2155968351","https://openalex.org/W2158782408","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2558634851","https://openalex.org/W2580909119","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2754517384","https://openalex.org/W2790162350","https://openalex.org/W2909112693","https://openalex.org/W2962769637","https://openalex.org/W2963120839","https://openalex.org/W2963477884","https://openalex.org/W2963864421","https://openalex.org/W2964001908","https://openalex.org/W2964043796","https://openalex.org/W2967129319","https://openalex.org/W2968095426","https://openalex.org/W2997896361","https://openalex.org/W4300799055","https://openalex.org/W4302570325","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6730616910","https://openalex.org/W6740801417","https://openalex.org/W6741002519","https://openalex.org/W6753069059","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2948333011","https://openalex.org/W4386619269","https://openalex.org/W4392903819","https://openalex.org/W1942758450","https://openalex.org/W2994972936","https://openalex.org/W2922338626","https://openalex.org/W4303645333","https://openalex.org/W4221067497","https://openalex.org/W4312745891","https://openalex.org/W2108010283"],"abstract_inverted_index":{"Learning-based":[0],"methods":[1,129],"have":[2],"been":[3],"used":[4],"to":[5,32,69,79,99,117,133],"program":[6],"robotic":[7,60],"tasks":[8],"in":[9,37,58,130],"recent":[10],"years.":[11],"However,":[12],"extensive":[13],"training":[14,120],"is":[15,67],"usually":[16],"required":[17],"not":[18],"only":[19],"for":[20,27,51],"the":[21,29,33,59,72,81,95,101],"initial":[22],"task":[23,35,53,61,75],"learning":[24,62,102],"but":[25,36],"also":[26,108],"generalizing":[28],"learned":[30,74],"model":[31,77,98],"same":[34],"different":[38],"environments.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43,107],"propose":[44],"a":[45,110],"novel":[46],"Deep":[47,87],"Reinforcement":[48],"Learning":[49],"algorithm":[50],"efficient":[52],"generalization":[54],"and":[55,93,104],"environment":[56,82],"adaptation":[57,83],"problem.":[63,84],"The":[64,85,122],"proposed":[65,86,123],"method":[66,91,124],"able":[68],"efficiently":[70],"generalize":[71],"previously":[73,96],"by":[76],"fusion":[78],"solve":[80],"Model":[88],"Fusion":[89],"(DMF)":[90],"reuses":[92],"combines":[94],"trained":[97],"improve":[100,119],"efficiency":[103],"results.":[105],"Besides,":[106],"introduce":[109],"Multi-objective":[111],"Guided":[112],"Reward":[113],"(MGR)":[114],"shaping":[115],"technique":[116],"further":[118],"efficiency.":[121],"was":[125],"benchmarked":[126],"with":[127],"previous":[128],"various":[131],"environments":[132],"validate":[134],"its":[135],"effectiveness.":[136]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
