{"id":"https://openalex.org/W3171711942","doi":"https://doi.org/10.1109/syscon48628.2021.9447080","title":"Optimization of Deep Reinforcement Learning with Hybrid Multi-Task Learning","display_name":"Optimization of Deep Reinforcement Learning with Hybrid Multi-Task Learning","publication_year":2021,"publication_date":"2021-04-15","ids":{"openalex":"https://openalex.org/W3171711942","doi":"https://doi.org/10.1109/syscon48628.2021.9447080","mag":"3171711942"},"language":"en","primary_location":{"id":"doi:10.1109/syscon48628.2021.9447080","is_oa":false,"landing_page_url":"https://doi.org/10.1109/syscon48628.2021.9447080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Systems Conference (SysCon)","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/A5008639759","display_name":"Nelson Vithayathil Varghese","orcid":"https://orcid.org/0000-0002-0792-1035"},"institutions":[{"id":"https://openalex.org/I39470171","display_name":"University of Ontario Institute of Technology","ror":"https://ror.org/016zre027","country_code":"CA","type":"education","lineage":["https://openalex.org/I39470171"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Nelson Vithayathil Varghese","raw_affiliation_strings":["Computer, and Software Engineering, Ontario Tech University, Oshawa, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Computer, and Software Engineering, Ontario Tech University, Oshawa, ON, Canada","institution_ids":["https://openalex.org/I39470171"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011840659","display_name":"Qusay H. Mahmoud","orcid":"https://orcid.org/0000-0003-0472-5757"},"institutions":[{"id":"https://openalex.org/I39470171","display_name":"University of Ontario Institute of Technology","ror":"https://ror.org/016zre027","country_code":"CA","type":"education","lineage":["https://openalex.org/I39470171"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Qusay H. Mahmoud","raw_affiliation_strings":["Computer, and Software Engineering, Ontario Tech University, Oshawa, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Computer, and Software Engineering, Ontario Tech University, Oshawa, ON, Canada","institution_ids":["https://openalex.org/I39470171"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008639759"],"corresponding_institution_ids":["https://openalex.org/I39470171"],"apc_list":null,"apc_paid":null,"fwci":0.4079,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67765759,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"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":0.9998999834060669,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9962000250816345,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9797000288963318,"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":0.930781364440918},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7992604374885559},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7457129955291748},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6197668313980103},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5733410716056824},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.557674765586853},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4553258419036865},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4550611972808838},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4328667223453522},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.4233090281486511},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10499539971351624},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.10359075665473938}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.930781364440918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7992604374885559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7457129955291748},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6197668313980103},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5733410716056824},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.557674765586853},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4553258419036865},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4550611972808838},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4328667223453522},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.4233090281486511},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10499539971351624},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.10359075665473938},{"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/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/syscon48628.2021.9447080","is_oa":false,"landing_page_url":"https://doi.org/10.1109/syscon48628.2021.9447080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Systems Conference (SysCon)","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":30,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2124175081","https://openalex.org/W2145339207","https://openalex.org/W2174786457","https://openalex.org/W2555488107","https://openalex.org/W2583761661","https://openalex.org/W2735995851","https://openalex.org/W2786036274","https://openalex.org/W2891076394","https://openalex.org/W2908261578","https://openalex.org/W2963199420","https://openalex.org/W2964043796","https://openalex.org/W2964615009","https://openalex.org/W3007452400","https://openalex.org/W3016764502","https://openalex.org/W3034419097","https://openalex.org/W3081310128","https://openalex.org/W4293534691","https://openalex.org/W4297797010","https://openalex.org/W4298174377","https://openalex.org/W6678114464","https://openalex.org/W6685726866","https://openalex.org/W6692846177","https://openalex.org/W6730027589","https://openalex.org/W6732467815","https://openalex.org/W6740879895","https://openalex.org/W6748638692","https://openalex.org/W6759097295","https://openalex.org/W6773895220","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W1966456942","https://openalex.org/W2930863966","https://openalex.org/W2754028433","https://openalex.org/W3148138296","https://openalex.org/W1882507001","https://openalex.org/W2126211886","https://openalex.org/W2367922714","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W3119422923"],"abstract_inverted_index":{"As":[0],"an":[1],"outcome":[2],"of":[3,33,47,78,89,127,152,156,162,172,185,189,205],"the":[4,38,45,75,90,153,173,183,203,238,248],"technological":[5],"advancements":[6],"occurred":[7],"within":[8,211,233],"artificial":[9],"intelligence":[10],"(AI)":[11],"domain":[12],"in":[13,125],"recent":[14],"times,":[15],"deep":[16,48,54,206],"learning":[17,28,35,40,50,58,63,104,117,199,208],"(DL)":[18],"has":[19,69],"been":[20],"established":[21],"its":[22],"position":[23],"as":[24,121,139,141],"a":[25,71,112,196,243],"prominent":[26],"representation":[27],"method":[29,118,184],"for":[30,148,202],"all":[31],"forms":[32],"machine":[34],"(ML),":[36],"including":[37],"reinforcement":[39,49,62,103,207],"(RL).":[41],"Subsequently,":[42],"leading":[43],"to":[44,99,107,159,176,194,246],"evolution":[46],"(DRL)":[51],"which":[52],"combines":[53],"learning's":[55],"high":[56],"representational":[57],"capabilities":[59],"with":[60,93,218,227],"current":[61],"methods.":[64],"Undoubtedly,":[65],"this":[66,94,149,178,190],"new":[67],"direction":[68],"caused":[70],"pivotal":[72],"role":[73],"towards":[74],"performance":[76,91],"optimization":[77,88,204],"intelligent":[79,100,132],"RL":[80],"systems":[81,101,133],"designed":[82,106],"by":[83,181,214],"following":[84],"model-free":[85],"based":[86],"methodology.":[87],"achieved":[92],"methodology":[95],"was":[96,119,150],"majorly":[97],"restricted":[98,154],"having":[102],"algorithms":[105],"learn":[108],"single":[109,115],"task":[110],"at":[111],"time.":[113],"Simultaneously,":[114],"task-based":[116],"observed":[120],"quite":[122],"less":[123],"efficient":[124],"terms":[126],"data,":[128],"especially":[129],"when":[130],"such":[131],"required":[134],"operate":[135],"under":[136],"too":[137],"complex":[138],"well":[140],"data":[142],"rich":[143],"conditions.":[144],"The":[145,221],"prime":[146],"reason":[147],"because":[151],"application":[155],"existing":[157],"methods":[158],"wide":[160],"range":[161],"scenarios,":[163],"and":[164,236],"associated":[165],"tasks":[166],"from":[167],"those":[168],"operating":[169,210],"environments.":[170],"One":[171],"possible":[174],"approaches":[175],"mitigate":[177],"issue":[179],"is":[180,193],"adopting":[182],"multi-task":[186,198],"learning.":[187],"Objective":[188],"research":[191],"paper":[192],"present":[195],"parallel":[197],"(PMTL)":[200],"approach":[201],"agents":[209],"two":[212],"different":[213],"semantically":[215],"similar":[216],"environments":[217],"related":[219],"tasks.":[220],"proposed":[222],"framework":[223],"will":[224],"be":[225],"built":[226],"multiple":[228],"individual":[229],"actor-critic":[230],"models":[231],"functioning":[232],"each":[234],"environment":[235],"transferring":[237],"knowledge":[239],"among":[240],"themselves":[241],"through":[242],"global":[244],"network":[245],"optimize":[247],"performance.":[249]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}