{"id":"https://openalex.org/W4388052812","doi":"https://doi.org/10.1109/tnnls.2023.3325633","title":"Deep Reinforcement Learning With Explicit Context Representation","display_name":"Deep Reinforcement Learning With Explicit Context Representation","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388052812","doi":"https://doi.org/10.1109/tnnls.2023.3325633","pmid":"https://pubmed.ncbi.nlm.nih.gov/37906492"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3325633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3325633","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":true,"oa_status":"green","oa_url":"https://orca.cardiff.ac.uk/id/eprint/163231/1/Ji%20Z.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046176579","display_name":"Francisco Munguia\u2010Galeano","orcid":"https://orcid.org/0000-0001-8397-3083"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Francisco Munguia-Galeano","raw_affiliation_strings":["School of Engineering, Cardiff University, Cardiff, U.K"],"raw_orcid":"https://orcid.org/0000-0001-8397-3083","affiliations":[{"raw_affiliation_string":"School of Engineering, Cardiff University, Cardiff, U.K","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004167801","display_name":"Ah\u2010Hwee Tan","orcid":"https://orcid.org/0000-0003-0378-4069"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ah-Hwee Tan","raw_affiliation_strings":["School of Computing and Information Systems, Singapore Management University, Bras Basah, Singapore","School of Computing and Information Systems, Singapore Management University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-0378-4069","affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University, Bras Basah, Singapore","institution_ids":["https://openalex.org/I79891267"]},{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University, Singapore, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068175770","display_name":"Ze Ji","orcid":"https://orcid.org/0000-0002-8968-9902"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ze Ji","raw_affiliation_strings":["School of Engineering, Cardiff University, Cardiff, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8968-9902","affiliations":[{"raw_affiliation_string":"School of Engineering, Cardiff University, Cardiff, U.K","institution_ids":["https://openalex.org/I79510175"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046176579"],"corresponding_institution_ids":["https://openalex.org/I79510175"],"apc_list":null,"apc_paid":null,"fwci":0.8385,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79031878,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"36","issue":"1","first_page":"419","last_page":"432"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9433000087738037,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9433000087738037,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9294000267982483,"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":0.8116886615753174},{"id":"https://openalex.org/keywords/affordance","display_name":"Affordance","score":0.7868205904960632},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7456769943237305},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.6922335624694824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6301296353340149},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6296805143356323},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5994083881378174},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4905907213687897},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4709385633468628},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4544428586959839},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4499156177043915},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4339355528354645},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4246410131454468},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.422402948141098},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34047621488571167},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.20126551389694214},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.172572523355484}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8116886615753174},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.7868205904960632},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7456769943237305},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.6922335624694824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6301296353340149},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6296805143356323},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5994083881378174},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4905907213687897},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4709385633468628},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4544428586959839},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4499156177043915},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4339355528354645},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4246410131454468},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.422402948141098},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34047621488571167},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.20126551389694214},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.172572523355484},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2023.3325633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3325633","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:37906492","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37906492","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":null},{"id":"pmh:oai:https://orca.cardiff.ac.uk:163231","is_oa":true,"landing_page_url":"https://orca.cardiff.ac.uk/view/cardiffauthors/A2482800H.html>","pdf_url":"https://orca.cardiff.ac.uk/id/eprint/163231/1/Ji%20Z.pdf","source":{"id":"https://openalex.org/S4306401195","display_name":"ORCA Online Research @Cardiff (Cardiff University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79510175","host_organization_name":"Cardiff University","host_organization_lineage":["https://openalex.org/I79510175"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"pmh:oai:https://orca.cardiff.ac.uk:163231","is_oa":true,"landing_page_url":"https://orca.cardiff.ac.uk/view/cardiffauthors/A2482800H.html>","pdf_url":"https://orca.cardiff.ac.uk/id/eprint/163231/1/Ji%20Z.pdf","source":{"id":"https://openalex.org/S4306401195","display_name":"ORCA Online Research @Cardiff (Cardiff University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79510175","host_organization_name":"Cardiff University","host_organization_lineage":["https://openalex.org/I79510175"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G478423709","display_name":null,"funder_award_id":"AISG2-RP-2020-019","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G6961989012","display_name":"PHYDL: Physics-informed Differentiable Learning for Robotic Manipulation of Viscous and Granular Media","funder_award_id":"EP/X018962/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8031890916","display_name":null,"funder_award_id":"EP/X018962/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4388052812.pdf"},"referenced_works_count":67,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W195596278","https://openalex.org/W1483019628","https://openalex.org/W2029130131","https://openalex.org/W2097381042","https://openalex.org/W2130935956","https://openalex.org/W2140135625","https://openalex.org/W2145339207","https://openalex.org/W2201581102","https://openalex.org/W2559960928","https://openalex.org/W2604763608","https://openalex.org/W2607014226","https://openalex.org/W2736601468","https://openalex.org/W2766099639","https://openalex.org/W2788862220","https://openalex.org/W2791797404","https://openalex.org/W2792645523","https://openalex.org/W2793798239","https://openalex.org/W2883132849","https://openalex.org/W2890822044","https://openalex.org/W2904453761","https://openalex.org/W2951799221","https://openalex.org/W2963099939","https://openalex.org/W2963276097","https://openalex.org/W2963301010","https://openalex.org/W2964043796","https://openalex.org/W2966477753","https://openalex.org/W2967352729","https://openalex.org/W2974778612","https://openalex.org/W2990622100","https://openalex.org/W3011371828","https://openalex.org/W3027412509","https://openalex.org/W3038721901","https://openalex.org/W3100789280","https://openalex.org/W3111420256","https://openalex.org/W3122963056","https://openalex.org/W3134939669","https://openalex.org/W3161040011","https://openalex.org/W3162904728","https://openalex.org/W3174474790","https://openalex.org/W3188522443","https://openalex.org/W3188541024","https://openalex.org/W3212887262","https://openalex.org/W4226452279","https://openalex.org/W4286910245","https://openalex.org/W4287329474","https://openalex.org/W4287708298","https://openalex.org/W4292756713","https://openalex.org/W4297964528","https://openalex.org/W4304480790","https://openalex.org/W6608012839","https://openalex.org/W6674600207","https://openalex.org/W6677067356","https://openalex.org/W6680657880","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6717230150","https://openalex.org/W6735939104","https://openalex.org/W6736057607","https://openalex.org/W6741002519","https://openalex.org/W6757469721","https://openalex.org/W6790190981","https://openalex.org/W6801798027","https://openalex.org/W6802559433","https://openalex.org/W6811203553"],"related_works":["https://openalex.org/W1972718289","https://openalex.org/W1791514435","https://openalex.org/W2346831895","https://openalex.org/W2248634132","https://openalex.org/W2295809616","https://openalex.org/W3049116993","https://openalex.org/W2070708245","https://openalex.org/W1541884709","https://openalex.org/W2589081601","https://openalex.org/W4319594507"],"abstract_inverted_index":{"Though":[0],"reinforcement":[1],"learning":[2,24],"(RL)":[3],"has":[4],"shown":[5],"an":[6,18,59,73],"outstanding":[7],"capability":[8],"for":[9,72,85],"solving":[10],"complex":[11],"computational":[12],"problems,":[13],"most":[14],"RL":[15,74],"algorithms":[16,167,201],"lack":[17],"explicit":[19,90],"method":[20],"that":[21,114,168,208],"would":[22],"allow":[23],"from":[25,63,150,155],"contextual":[26,101,148,214],"information.":[27],"On":[28],"the":[29,44,116,119,131,134,139,151,156,161,196,199,210,223],"other":[30],"hand,":[31],"humans":[32],"often":[33],"use":[34,213],"context":[35,91],"to":[36,49,76,78,110,130,146],"identify":[37],"patterns":[38],"and":[39,153,186,198],"relations":[40],"among":[41],"elements":[42],"in":[43,121,143,202,217],"environment,":[45],"along":[46],"with":[47,128],"how":[48],"avoid":[50],"making":[51],"wrong":[52,61],"actions.":[53],"However,":[54],"what":[55],"may":[56],"seem":[57],"like":[58],"obviously":[60],"decision":[62],"a":[64,83,112],"human":[65],"perspective":[66],"could":[67],"take":[68],"hundreds":[69],"of":[70,118,133,138,222],"steps":[71,221],"agent":[75],"learn":[77,154,169],"avoid.":[79],"This":[80],"article":[81],"proposes":[82],"framework":[84,95,141,162,197],"discrete":[86,204],"environments":[87],"called":[88],"Iota":[89,172,176,181,187],"representation":[92],"(IECR).":[93],"The":[94,136],"involves":[96],"representing":[97],"each":[98],"state":[99],"using":[100,170],"key":[102],"frames":[103],"(CKFs),":[104],"which":[105,212],"can":[106],"then":[107],"be":[108],"used":[109],"extract":[111,147],"function":[113],"represents":[115],"affordances":[117,132],"state;":[120],"addition,":[122],"two":[123],"loss":[124],"functions":[125],"are":[126],"introduced":[127],"respect":[129],"state.":[135],"novelty":[137],"IECR":[140],"lies":[142],"its":[144],"capacity":[145],"information":[149],"environment":[152],"CKFs'":[157],"representation.":[158],"We":[159,206],"validate":[160],"by":[163],"developing":[164],"four":[165],"new":[166,200],"context:":[171],"deep":[173,178,183,190],"Q-network":[174,179,184,191],"(IDQN),":[175],"double":[177,189],"(IDDQN),":[180],"dueling":[182,188],"(IDuDQN),":[185],"(IDDDQN).":[192],"Furthermore,":[193],"we":[194],"evaluate":[195],"five":[203],"environments.":[205],"show":[207],"all":[209],"algorithms,":[211],"information,":[215],"converge":[216],"around":[218],"40000":[219],"training":[220],"neural":[224],"networks,":[225],"significantly":[226],"outperforming":[227],"their":[228],"state-of-the-art":[229],"equivalents.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2025-10-10T00:00:00"}