{"id":"https://openalex.org/W7164807489","doi":"https://doi.org/10.1007/s00521-026-12209-6","title":"T2f: Actor-critic reinforcement learning for time-series forecasting","display_name":"T2f: Actor-critic reinforcement learning for time-series forecasting","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7164807489","doi":"https://doi.org/10.1007/s00521-026-12209-6"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-026-12209-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-026-12209-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-026-12209-6.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-026-12209-6.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070564048","display_name":"Jo\u00e3o Sousa","orcid":"https://orcid.org/0000-0001-5600-9707"},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Jo\u00e3o Sousa","raw_affiliation_strings":["NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa, Campus de Campolide, Lisboa, 1070-312, Portugal"],"raw_orcid":"https://orcid.org/0000-0001-5600-9707","affiliations":[{"raw_affiliation_string":"NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa, Campus de Campolide, Lisboa, 1070-312, Portugal","institution_ids":["https://openalex.org/I83558840"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138653066","display_name":"Roberto Henriques","orcid":null},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Roberto Henriques","raw_affiliation_strings":["NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa, Campus de Campolide, Lisboa, 1070-312, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa, Campus de Campolide, Lisboa, 1070-312, Portugal","institution_ids":["https://openalex.org/I83558840"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5070564048"],"corresponding_institution_ids":["https://openalex.org/I83558840"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74520372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"12","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.5273000001907349,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.5273000001907349,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.11739999800920486,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T11052","display_name":"Energy Load and Power Forecasting","score":0.07919999957084656,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8134999871253967},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.7246000170707703},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.519599974155426},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5034000277519226},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.39239999651908875},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.38960000872612},{"id":"https://openalex.org/keywords/mean-squared-prediction-error","display_name":"Mean squared prediction error","score":0.3880999982357025},{"id":"https://openalex.org/keywords/mean-absolute-error","display_name":"Mean absolute error","score":0.38179999589920044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8274999856948853},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8134999871253967},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.7246000170707703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6819999814033508},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6284999847412109},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.519599974155426},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5034000277519226},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.3880999982357025},{"id":"https://openalex.org/C188154048","wikidata":"https://www.wikidata.org/wiki/Q6803609","display_name":"Mean absolute error","level":3,"score":0.38179999589920044},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27379998564720154},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.26179999113082886}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00521-026-12209-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-026-12209-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-026-12209-6.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s00521-026-12209-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-026-12209-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-026-12209-6.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7803040742874146}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323459","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7164807489.pdf","grobid_xml":"https://content.openalex.org/works/W7164807489.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W1537430301","https://openalex.org/W1590183771","https://openalex.org/W1603903339","https://openalex.org/W1605276600","https://openalex.org/W1986528915","https://openalex.org/W1991135386","https://openalex.org/W1993387039","https://openalex.org/W1999996900","https://openalex.org/W2003602843","https://openalex.org/W2007272376","https://openalex.org/W2016210396","https://openalex.org/W2038601479","https://openalex.org/W2079563517","https://openalex.org/W2100483895","https://openalex.org/W2136848157","https://openalex.org/W2138996412","https://openalex.org/W2147028502","https://openalex.org/W2158840489","https://openalex.org/W2161020850","https://openalex.org/W2163922914","https://openalex.org/W2329494830","https://openalex.org/W2344786740","https://openalex.org/W2613328025","https://openalex.org/W2746553466","https://openalex.org/W2747599906","https://openalex.org/W2753069234","https://openalex.org/W2775056555","https://openalex.org/W2808800115","https://openalex.org/W2889512547","https://openalex.org/W2890096158","https://openalex.org/W2907537824","https://openalex.org/W2909973217","https://openalex.org/W2962752580","https://openalex.org/W2964404039","https://openalex.org/W2966607134","https://openalex.org/W2968728157","https://openalex.org/W2980994438","https://openalex.org/W3015316773","https://openalex.org/W3110846353","https://openalex.org/W3124442571","https://openalex.org/W3125070724","https://openalex.org/W3127561923","https://openalex.org/W3171884590","https://openalex.org/W3172514114","https://openalex.org/W3177318507","https://openalex.org/W3196951408","https://openalex.org/W4206173445","https://openalex.org/W4230410911","https://openalex.org/W4231057675","https://openalex.org/W4241115065","https://openalex.org/W4248437541","https://openalex.org/W4283807683","https://openalex.org/W4291014897","https://openalex.org/W4292022450","https://openalex.org/W4295754656","https://openalex.org/W4304163163","https://openalex.org/W4385763767","https://openalex.org/W4392594314","https://openalex.org/W4402243001","https://openalex.org/W4405562901","https://openalex.org/W4414447071","https://openalex.org/W6907814131","https://openalex.org/W6945316566"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Time-series":[1],"forecasting":[2,27,80],"of":[3],"multiple":[4],"related":[5],"sequences":[6],"presents":[7],"unique":[8],"challenges":[9],"due":[10],"to":[11,140,146,171,185],"the":[12,38,97,114],"complex":[13,194],"interplay":[14],"between":[15],"individual":[16],"series":[17],"characteristics":[18],"and":[19,48,55,75,143],"global":[20,49],"patterns.":[21],"We":[22],"present":[23],"T2f":[24,45,91,131,161],",":[25],"a":[26],"method":[28,70],"combining":[29],"ensemble":[30,119],"learning":[31,56,64],"with":[32,62,82,113,174,193],"an":[33],"actor-critic":[34],"architecture":[35,54],"based":[36],"on":[37,150,162,191],"Twin":[39],"Delayed":[40],"Deep":[41],"Deterministic":[42],"algorithm":[43],"(TD3).":[44],"balances":[46],"local":[47],"patterns":[50],"through":[51],"both":[52],"its":[53],"approaches,":[57],"integrating":[58],"transformer-based":[59],"pattern":[60],"recognition":[61],"reinforcement":[63],"for":[65,187],"dynamic":[66],"model":[67],"selection.":[68],"Our":[69],"incorporates":[71],"temporal":[72,108,195],"attention":[73,109],"mechanisms":[74],"context-aware":[76],"error":[77,102,135],"measurement,":[78],"aligning":[79],"objectives":[81],"practical":[83],"decision-making":[84],"priorities.":[85],"Comprehensive":[86],"ablation":[87],"studies":[88],"demonstrate":[89],"that":[90],"\u2019s":[92],"components":[93],"provide":[94],"synergistic":[95],"benefits:":[96],"TD3-based":[98],"optimizer":[99],"contributes":[100],"18.8%":[101],"reduction":[103],"over":[104,122,137],"static":[105],"weighting,":[106],"while":[107],"adds":[110],"8.0%":[111],"improvement,":[112],"integrated":[115],"system":[116],"outperforming":[117],"simple":[118],"baselines":[120],"by":[121,136],"20%.":[123],"Experimental":[124],"results":[125],"across":[126],"five":[127],"diverse":[128],"datasets":[129,192],"indicate":[130],"reduced":[132],"mean":[133],"absolute":[134],"30%":[138],"compared":[139,184],"statistical":[141],"models":[142,158],"achieved":[144],"up":[145],"40%":[147],"better":[148],"performance":[149,180],"context-weighted":[151],"metrics":[152],"than":[153],"competing":[154],"approaches.":[155],"While":[156],"specialized":[157],"occasionally":[159],"outperformed":[160],"highly":[163],"regular":[164],"patterns,":[165],"it":[166],"consistently":[167],"showed":[168],"superior":[169],"adaptability":[170],"contextual":[172],"weights":[173],"faster":[175],"convergence,":[176],"typically":[177],"reaching":[178],"near-optimal":[179],"within":[181],"25":[182],"epochs":[183],"40+":[186],"alternative":[188],"methods,":[189],"particularly":[190],"dynamics.":[196]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-06-16T00:00:00"}