{"id":"https://openalex.org/W7167062296","doi":"https://doi.org/10.1016/j.engappai.2026.115524","title":"Deep reinforcement learning in applied control: Challenges, analysis, and insights","display_name":"Deep reinforcement learning in applied control: Challenges, analysis, and insights","publication_year":2026,"publication_date":"2026-07-02","ids":{"openalex":"https://openalex.org/W7167062296","doi":"https://doi.org/10.1016/j.engappai.2026.115524"},"language":"en","primary_location":{"id":"doi:10.1016/j.engappai.2026.115524","doi":"https://doi.org/10.1016/j.engappai.2026.115524","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.engappai.2026.115524","pdf_url":null,"source":{"id":"https://openalex.org/S900972176","display_name":"Engineering Applications of Artificial Intelligence","issn_l":"0952-1976","issn":["0952-1976","1873-6769"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-c","cwts-core","dongbi-d","jufo-2","ki-jl-1","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Engineering Applications of Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.engappai.2026.115524","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115001477","display_name":"Klinsmann Agyei","orcid":"https://orcid.org/0009-0002-2649-6991","observed_orcids":["https://orcid.org/0009-0002-2649-6991"]},"institutions":[{"id":"https://openalex.org/I141584323","display_name":"University of Hertfordshire","ror":"https://ror.org/0267vjk41","country_code":"GB","type":"education","lineage":["https://openalex.org/I141584323"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Klinsmann Agyei","raw_affiliation_strings":["University of Hertfordshire, School of Physics, Engineering and Computer Science, Hatfield, AL10 9AB, Hertfordshire, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0002-2649-6991","affiliations":[{"raw_affiliation_string":"University of Hertfordshire, School of Physics, Engineering and Computer Science, Hatfield, AL10 9AB, Hertfordshire, United Kingdom","institution_ids":["https://openalex.org/I141584323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020535690","display_name":"Pouria Sarhadi","orcid":"https://orcid.org/0000-0002-6004-676X","observed_orcids":["https://orcid.org/0000-0002-6004-676X"]},"institutions":[{"id":"https://openalex.org/I141584323","display_name":"University of Hertfordshire","ror":"https://ror.org/0267vjk41","country_code":"GB","type":"education","lineage":["https://openalex.org/I141584323"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Pouria Sarhadi","raw_affiliation_strings":["University of Hertfordshire, School of Physics, Engineering and Computer Science, Hatfield, AL10 9AB, Hertfordshire, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-6004-676X","affiliations":[{"raw_affiliation_string":"University of Hertfordshire, School of Physics, Engineering and Computer Science, Hatfield, AL10 9AB, Hertfordshire, United Kingdom","institution_ids":["https://openalex.org/I141584323"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070558949","display_name":"Daniel Polani","orcid":"https://orcid.org/0000-0002-3233-5847","observed_orcids":["https://orcid.org/0000-0002-3233-5847"]},"institutions":[{"id":"https://openalex.org/I141584323","display_name":"University of Hertfordshire","ror":"https://ror.org/0267vjk41","country_code":"GB","type":"education","lineage":["https://openalex.org/I141584323"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniel Polani","raw_affiliation_strings":["University of Hertfordshire, School of Physics, Engineering and Computer Science, Hatfield, AL10 9AB, Hertfordshire, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-3233-5847","affiliations":[{"raw_affiliation_string":"University of Hertfordshire, School of Physics, Engineering and Computer Science, Hatfield, AL10 9AB, Hertfordshire, United Kingdom","institution_ids":["https://openalex.org/I141584323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5020535690"],"corresponding_institution_ids":["https://openalex.org/I141584323"],"apc_list":{"value":3200,"currency":"USD","value_usd":3200},"apc_paid":{"value":3200,"currency":"USD","value_usd":3200},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.49083223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"181","issue":null,"first_page":"115524","last_page":"115524"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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":0.0013000000035390258,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.8240000009536743},{"id":"https://openalex.org/keywords/applied-control","display_name":"applied control","score":0.824999988079071},{"id":"https://openalex.org/keywords/flexible-mechanical-systems","display_name":"flexible mechanical systems","score":0.9750000238418579},{"id":"https://openalex.org/keywords/aerial-robots","display_name":"autonomous drones","score":0.9110000133514404},{"id":"https://openalex.org/keywords/quadrotor","display_name":"quadrotor","score":0.9599999785423279},{"id":"https://openalex.org/keywords/actuator-saturation","display_name":"actuator saturation","score":0.8619999885559082},{"id":"https://openalex.org/keywords/sim-to-real-transfer","display_name":"sim-to-real transfer","score":0.9039999842643738},{"id":"https://openalex.org/keywords/robustness","display_name":"robustness","score":0.6600000262260437},{"id":"https://openalex.org/keywords/model-uncertainty","display_name":"model uncertainty","score":0.6600000262260437},{"id":"https://openalex.org/keywords/reward-function-design","display_name":"reward function design","score":0.7540000081062317},{"id":"https://openalex.org/keywords/tracking-performance","display_name":"tracking performance","score":0.46000000834465027},{"id":"https://openalex.org/keywords/disturbance-rejection","display_name":"disturbance rejection","score":0.4519999921321869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8068000078201294},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7249000072479248},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5637000203132629},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5230000019073486},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4544999897480011},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.40720000863075256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4041999876499176},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4016999900341034},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C14781684","wikidata":"https://www.wikidata.org/wiki/Q3983320","display_name":"Settling time","level":3,"score":0.3716999888420105},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3070000112056732},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C91581856","wikidata":"https://www.wikidata.org/wiki/Q2707001","display_name":"Nonlinear control","level":3,"score":0.27950000762939453},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27649998664855957},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.engappai.2026.115524","doi":"https://doi.org/10.1016/j.engappai.2026.115524","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.engappai.2026.115524","pdf_url":null,"source":{"id":"https://openalex.org/S900972176","display_name":"Engineering Applications of Artificial Intelligence","issn_l":"0952-1976","issn":["0952-1976","1873-6769"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-c","cwts-core","dongbi-d","jufo-2","ki-jl-1","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Engineering Applications of Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:uhra.herts.ac.uk:27175","doi":null,"is_oa":true,"landing_page_url":"https://uhra.herts.ac.uk/id/eprint/27175/1/DRL_Final.pdf","pdf_url":"https://uhra.herts.ac.uk/id/eprint/27175/2/1-s2.0-S0952197626018087-main.pdf","source":{"id":"https://openalex.org/S4306400241","display_name":"University of Hertfordshire Research Archive (University of Hertfordshire)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I141584323","host_organization_name":"University of Hertfordshire","host_organization_lineage":["https://openalex.org/I141584323"],"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":"Article"}],"best_oa_location":{"id":"doi:10.1016/j.engappai.2026.115524","doi":"https://doi.org/10.1016/j.engappai.2026.115524","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.engappai.2026.115524","pdf_url":null,"source":{"id":"https://openalex.org/S900972176","display_name":"Engineering Applications of Artificial Intelligence","issn_l":"0952-1976","issn":["0952-1976","1873-6769"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-c","cwts-core","dongbi-d","jufo-2","ki-jl-1","norway-1","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Engineering Applications of Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/14","display_name":"Life below water","score":0.7163495421409607}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2062578843","https://openalex.org/W2127409557","https://openalex.org/W2192201333","https://openalex.org/W2749614434","https://openalex.org/W2774785892","https://openalex.org/W2810677299","https://openalex.org/W2822752092","https://openalex.org/W2897661175","https://openalex.org/W2955319481","https://openalex.org/W2990747716","https://openalex.org/W2992833799","https://openalex.org/W3028022204","https://openalex.org/W3100789280","https://openalex.org/W3142818324","https://openalex.org/W3211847530","https://openalex.org/W4283160467","https://openalex.org/W4323662139","https://openalex.org/W4360876082","https://openalex.org/W4385989106","https://openalex.org/W4389827874","https://openalex.org/W4391661523","https://openalex.org/W4392901795","https://openalex.org/W4396542455","https://openalex.org/W4401979752","https://openalex.org/W4409348659","https://openalex.org/W7118162210","https://openalex.org/W7124243520"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2],"(DRL)":[3],"algorithms":[4,237],"have":[5],"shown":[6],"increasing":[7],"promise":[8],"for":[9,170,186,228],"autonomous":[10],"decision-making":[11],"and":[12,94,112,118,123,143,159,173,184,193,224,247],"continuous":[13],"control,":[14,93],"yet":[15],"their":[16],"practical":[17,231],"value":[18],"relative":[19],"to":[20,26,55],"established":[21],"control":[22,74,82,133,178,236],"methods":[23,122],"remains":[24,47,179],"difficult":[25],"assess":[27],"under":[28],"realistic":[29],"control-engineering":[30],"conditions.":[31,114,161,189],"Existing":[32],"evaluations":[33],"are":[34,52],"often":[35],"narrow,":[36],"application-specific,":[37],"or":[38],"based":[39],"on":[40,153,210],"inconsistent":[41],"assumptions.":[42],"As":[43],"a":[44,61,72,77,211,222,252],"result,":[45],"it":[46],"unclear":[48],"when":[49],"learned":[50,197],"controllers":[51,70,163,198],"suitable":[53],"alternatives":[54],"conventional":[56,248],"designs.":[57],"This":[58,115,250],"paper":[59],"presents":[60],"systematic":[62],"assessment":[63],"framework":[64,98],"that":[65,149,255],"compares":[66],"four":[67],"prominent":[68],"DRL":[69],"with":[71],"classical":[73,204],"baseline":[75,205],"across":[76,121],"diverse":[78],"set":[79],"of":[80,233],"applied":[81,239],"problems,":[83],"including":[84],"non-minimum":[85],"phase":[86],"dynamics,":[87,158,195],"flexible":[88],"mechanical":[89],"systems,":[90],"nonlinear":[91],"marine":[92],"aerial":[95],"robotics.":[96],"The":[97,125,146,219],"standardises":[99],"modelling":[100],"assumptions,":[101],"reward":[102],"design,":[103],"controller":[104],"tuning,":[105],"computational":[106],"budgets,":[107],"performance":[108,150],"metrics,":[109],"robustness":[110,141],"tests,":[111],"deployment":[113,209],"allows":[116],"fair":[117],"reproducible":[119,225],"analysis":[120],"applications.":[124],"evaluation":[126],"covers":[127],"tracking":[128],"accuracy,":[129,182],"settling":[130],"time,":[131],"overshoot,":[132],"effort,":[134],"actuator":[135],"saturation,":[136],"disturbance":[137],"rejection,":[138],"model":[139],"uncertainty,":[140],"margins,":[142],"sim-to-real":[144,217],"transfer.":[145,218],"results":[147],"show":[148],"depends":[151],"strongly":[152],"the":[154,196,203,230,243],"algorithmic":[155],"structure,":[156],"system":[157],"operating":[160,175],"Learned":[162],"provide":[164],"advantages":[165],"in":[166,181,238],"some":[167],"cases,":[168],"particularly":[169],"nonlinearities,":[171],"constraints,":[172],"uncertain":[174],"regimes.":[176],"Classical":[177],"competitive":[180],"simplicity,":[183],"reliability":[185],"several":[187],"benchmark":[188],"Under":[190],"combined":[191],"saturation":[192],"unmodelled":[194],"maintained":[199],"stable":[200,216],"operation":[201],"where":[202],"became":[206],"unstable.":[207],"Real-time":[208],"quadrotor":[212],"platform":[213],"further":[214],"demonstrated":[215],"study":[220],"establishes":[221],"rigorous":[223],"evidence":[226],"base":[227],"assessing":[229],"suitability":[232],"these":[234],"data-driven":[235],"control.":[240,249],"It":[241],"clarifies":[242],"trade-offs":[244],"between":[245],"learning-based":[246],"addresses":[251],"critical":[253],"gap":[254],"cannot":[256],"be":[257],"easily":[258],"inferred":[259],"from":[260],"isolated,":[261],"system-specific":[262],"studies.":[263]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2026-07-03T00:00:00"}