{"id":"https://openalex.org/W4385810162","doi":"https://doi.org/10.1007/s00521-023-08845-x","title":"ACRE: Actor-Critic with Reward-Preserving Exploration","display_name":"ACRE: Actor-Critic with Reward-Preserving Exploration","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385810162","doi":"https://doi.org/10.1007/s00521-023-08845-x"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-023-08845-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-023-08845-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-023-08845-x.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/s00521-023-08845-x.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046634751","display_name":"Athanasios Ch. Kapoutsis","orcid":"https://orcid.org/0000-0002-1688-036X"},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]},{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Athanasios Ch. Kapoutsis","raw_affiliation_strings":["Information Technologies Institute, The Centre for Research & Technology, Hellas, 6th km Charilaou-Thermi Rd, 57001, Thessaloniki, Thermi, Greece"],"raw_orcid":"https://orcid.org/0000-0002-1688-036X","affiliations":[{"raw_affiliation_string":"Information Technologies Institute, The Centre for Research & Technology, Hellas, 6th km Charilaou-Thermi Rd, 57001, Thessaloniki, Thermi, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051403970","display_name":"Dimitrios Koutras","orcid":"https://orcid.org/0000-0001-9774-5591"},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]},{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dimitrios I. Koutras","raw_affiliation_strings":["Information Technologies Institute, The Centre for Research & Technology, Hellas, 6th km Charilaou-Thermi Rd, 57001, Thessaloniki, Thermi, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technologies Institute, The Centre for Research & Technology, Hellas, 6th km Charilaou-Thermi Rd, 57001, Thessaloniki, Thermi, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014467032","display_name":"Christos Korkas","orcid":"https://orcid.org/0000-0002-2491-2659"},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]},{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Christos D. Korkas","raw_affiliation_strings":["Information Technologies Institute, The Centre for Research & Technology, Hellas, 6th km Charilaou-Thermi Rd, 57001, Thessaloniki, Thermi, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technologies Institute, The Centre for Research & Technology, Hellas, 6th km Charilaou-Thermi Rd, 57001, Thessaloniki, Thermi, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071596476","display_name":"Elias B. Kosmatopoulos","orcid":"https://orcid.org/0000-0002-3735-4238"},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]},{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Elias B. Kosmatopoulos","raw_affiliation_strings":["Information Technologies Institute, The Centre for Research & Technology, Hellas, 6th km Charilaou-Thermi Rd, 57001, Thessaloniki, Thermi, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technologies Institute, The Centre for Research & Technology, Hellas, 6th km Charilaou-Thermi Rd, 57001, Thessaloniki, Thermi, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046634751"],"corresponding_institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.3779,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67880111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"35","issue":"30","first_page":"22563","last_page":"22576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9754999876022339,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.9728999733924866,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7456362843513489},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7339543700218201},{"id":"https://openalex.org/keywords/acre","display_name":"Acre","score":0.6514453887939453},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5975748300552368},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4867994487285614},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4817333519458771},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.45388302206993103},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.4218602180480957},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4160439074039459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38582655787467957},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.24303770065307617},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16054704785346985},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08071568608283997},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.07946419715881348}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7456362843513489},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7339543700218201},{"id":"https://openalex.org/C48508581","wikidata":"https://www.wikidata.org/wiki/Q4675074","display_name":"Acre","level":2,"score":0.6514453887939453},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5975748300552368},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4867994487285614},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4817333519458771},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.45388302206993103},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.4218602180480957},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4160439074039459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38582655787467957},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.24303770065307617},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16054704785346985},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08071568608283997},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.07946419715881348},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C54286561","wikidata":"https://www.wikidata.org/wiki/Q397350","display_name":"Agroforestry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00521-023-08845-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-023-08845-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-023-08845-x.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/s00521-023-08845-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-023-08845-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-023-08845-x.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":[{"id":"https://metadata.un.org/sdg/1","score":0.41999998688697815,"display_name":"No poverty"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320318628","display_name":"Hellenic Academic Libraries Link","ror":null},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385810162.pdf","grobid_xml":"https://content.openalex.org/works/W4385810162.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2158782408","https://openalex.org/W2257979135","https://openalex.org/W2575705757","https://openalex.org/W2963523627","https://openalex.org/W3121342653","https://openalex.org/W3127756416","https://openalex.org/W3206039816","https://openalex.org/W3207033168","https://openalex.org/W4214717370","https://openalex.org/W4292749546","https://openalex.org/W4385430550","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4225269853"],"abstract_inverted_index":{"Abstract":[0],"While":[1],"reinforcement":[2],"learning":[3,188],"(RL)":[4],"algorithms":[5,44],"have":[6],"generated":[7],"impressive":[8],"strategies":[9],"for":[10,83],"a":[11,39,76,98,147,179],"wide":[12],"range":[13,180],"of":[14,113,119,181],"tasks,":[15],"the":[16,26,55,63,69,81,89,101,117,139,153],"performance":[17],"improvements":[18,173],"in":[19,116,171,178],"continuous-domain,":[20],"real-world":[21],"problems":[22],"do":[23],"not":[24],"follow":[25],"same":[27],"trend.":[28],"Poor":[29],"exploration":[30,52,71],"and":[31,96,106,121,125],"quick":[32],"convergence":[33],"to":[34,46,65,108,151],"locally":[35],"optimal":[36],"solutions":[37],"play":[38],"dominant":[40],"role.":[41],"Advanced":[42],"RL":[43,134,176,184],"attempt":[45],"mitigate":[47],"this":[48],"issue":[49],"by":[50],"introducing":[51],"signals":[53,67],"during":[54],"training":[56],"procedure.":[57],"This":[58],"successful":[59],"integration":[60],"has":[61],"paved":[62],"way":[64,118],"introduce":[66],"from":[68,189],"intrinsic":[70,126],"branch.":[72],"ACRE":[73,114,128,143,169],"algorithm":[74,135],"is":[75,129,144,195],"framework":[77],"that":[78,136],"concretely":[79],"describes":[80],"conditions":[82],"such":[84,164,186],"an":[85,130,165],"integration,":[86],"avoiding":[87],"transforming":[88],"Markov":[90],"decision":[91],"process":[92],"into":[93],"time":[94],"varying,":[95],"as":[97,187],"result,":[99],"making":[100],"whole":[102],"optimization":[103],"scheme":[104],"brittle":[105],"susceptible":[107],"instability.":[109],"The":[110],"key":[111],"distinction":[112],"lies":[115],"handling":[120],"storing":[122],"both":[123],"extrinsic":[124],"rewards.":[127],"off-policy,":[131],"actor-critic":[132],"style":[133],"separately":[137],"approximates":[138],"forward":[140],"novelty":[141],"return.":[142],"shipped":[145],"with":[146],"Gaussian":[148],"mixture":[149],"model":[150],"calculate":[152],"instantaneous":[154],"novelty;":[155],"however,":[156],"different":[157],"options":[158],"could":[159],"also":[160],"be":[161],"integrated.":[162],"Using":[163],"effective":[166],"early":[167],"exploration,":[168],"results":[170],"substantial":[172],"over":[174],"alternative":[175],"methods,":[177],"continuous":[182],"control":[183],"environments,":[185],"policy-misleading":[190],"reward":[191],"signals.":[192],"Open-source":[193],"implementation":[194],"available":[196],"here:":[197],"https://github.com/athakapo/ACRE":[198],".":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}
