{"id":"https://openalex.org/W7077052549","doi":"https://doi.org/10.1017/s0269888925100052","title":"An empirical investigation of value-based multi-objective reinforcement learning for stochastic environments","display_name":"An empirical investigation of value-based multi-objective reinforcement learning for stochastic environments","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7077052549","doi":"https://doi.org/10.1017/s0269888925100052"},"language":"en","primary_location":{"id":"doi:10.1017/s0269888925100052","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s0269888925100052","pdf_url":null,"source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1017/s0269888925100052","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kewen Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I149672521","display_name":"Federation University","ror":"https://ror.org/05qbzwv83","country_code":"AU","type":"education","lineage":["https://openalex.org/I149672521"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Kewen Ding","raw_affiliation_strings":["Federation University Australia"],"affiliations":[{"raw_affiliation_string":"Federation University Australia","institution_ids":["https://openalex.org/I149672521"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Peter Vamplew","orcid":"https://orcid.org/0000-0002-8687-4424"},"institutions":[{"id":"https://openalex.org/I149672521","display_name":"Federation University","ror":"https://ror.org/05qbzwv83","country_code":"AU","type":"education","lineage":["https://openalex.org/I149672521"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Peter Vamplew","raw_affiliation_strings":["Federation University Australia"],"affiliations":[{"raw_affiliation_string":"Federation University Australia","institution_ids":["https://openalex.org/I149672521"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cameron Foale","orcid":null},"institutions":[{"id":"https://openalex.org/I149672521","display_name":"Federation University","ror":"https://ror.org/05qbzwv83","country_code":"AU","type":"education","lineage":["https://openalex.org/I149672521"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Cameron Foale","raw_affiliation_strings":["Federation University Australia"],"affiliations":[{"raw_affiliation_string":"Federation University Australia","institution_ids":["https://openalex.org/I149672521"]}]},{"author_position":"last","author":{"id":null,"display_name":"Richard Dazeley","orcid":null},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Richard Dazeley","raw_affiliation_strings":["Deakin University"],"affiliations":[{"raw_affiliation_string":"Deakin University","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149672521"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6669409,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10978","display_name":"Prenatal Screening and Diagnostics","score":0.37389999628067017,"subfield":{"id":"https://openalex.org/subfields/2735","display_name":"Pediatrics, Perinatology and Child Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10978","display_name":"Prenatal Screening and Diagnostics","score":0.37389999628067017,"subfield":{"id":"https://openalex.org/subfields/2735","display_name":"Pediatrics, Perinatology and Child Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10290","display_name":"Pregnancy and preeclampsia studies","score":0.06300000101327896,"subfield":{"id":"https://openalex.org/subfields/2729","display_name":"Obstetrics and Gynecology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11290","display_name":"Preterm Birth and Chorioamnionitis","score":0.041200000792741776,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7793999910354614},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6032000184059143},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5809999704360962},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5569000244140625},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.46880000829696655},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.3476000130176544},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.3091999888420105}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7793999910354614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6692000031471252},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6032000184059143},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5809999704360962},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5569000244140625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49399998784065247},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.450300008058548},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34220001101493835},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C127491075","wikidata":"https://www.wikidata.org/wiki/Q7617825","display_name":"Stochastic modelling","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C137631369","wikidata":"https://www.wikidata.org/wiki/Q7617831","display_name":"Stochastic programming","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.27709999680519104},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.2712000012397766}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s0269888925100052","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s0269888925100052","pdf_url":null,"source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1017/s0269888925100052","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s0269888925100052","pdf_url":null,"source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W47799525","https://openalex.org/W1543572792","https://openalex.org/W1834963927","https://openalex.org/W1988210060","https://openalex.org/W2012612381","https://openalex.org/W2060846151","https://openalex.org/W2095602422","https://openalex.org/W2102660061","https://openalex.org/W2109910161","https://openalex.org/W2117428849","https://openalex.org/W2666874989","https://openalex.org/W2786038981","https://openalex.org/W2892165885","https://openalex.org/W2969489701","https://openalex.org/W3034757316","https://openalex.org/W3035432460","https://openalex.org/W3126403556","https://openalex.org/W3138191140","https://openalex.org/W4285588358","https://openalex.org/W4285603402","https://openalex.org/W4287266177","https://openalex.org/W4290987548","https://openalex.org/W4318769376","https://openalex.org/W4323358772","https://openalex.org/W4397288804","https://openalex.org/W4405198165","https://openalex.org/W6629734328","https://openalex.org/W6802826383","https://openalex.org/W6987302220"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"One":[1],"common":[2],"approach":[3,32],"to":[4,12],"solve":[5],"multi-objective":[6,89],"reinforcement":[7],"learning":[8],"(MORL)":[9],"problems":[10],"is":[11],"extend":[13],"conventional":[14],"Q-learning":[15,68,90],"by":[16],"using":[17],"vector":[18],"Q-values":[19],"in":[20,33],"combination":[21],"with":[22,30,64,77],"a":[23,55],"utility":[24],"function.":[25],"However":[26],"issues":[27],"can":[28],"arise":[29],"this":[31],"the":[34,43,59,62,71,87,100,109,113,119],"context":[35],"of":[36,58,86,102,112,123],"stochastic":[37,78],"environments,":[38],"particularly":[39],"when":[40],"optimising":[41],"for":[42,74],"scalarised":[44],"expected":[45],"reward":[46,95],"(SER)":[47],"criterion.":[48],"This":[49],"paper":[50],"extends":[51],"prior":[52],"research,":[53],"providing":[54],"detailed":[56],"examination":[57],"factors":[60],"influencing":[61],"frequency":[63],"which":[65],"value-based":[66],"MORL":[67],"algorithms":[69],"learn":[70],"SER-optimal":[72],"policy":[73],"an":[75],"environment":[76],"state":[79],"transitions.":[80],"We":[81],"empirically":[82],"examine":[83],"several":[84],"variations":[85],"core":[88],"algorithm":[91],"as":[92,94],"well":[93],"engineering":[96],"approaches":[97],"and":[98,121],"demonstrate":[99],"limitations":[101],"these":[103,124],"methods.":[104],"In":[105],"particular,":[106],"we":[107],"highlight":[108],"critical":[110],"impact":[111],"noisy":[114],"Q-value":[115],"estimates":[116],"issue":[117],"on":[118],"stability":[120],"convergence":[122],"algorithms.":[125]},"counts_by_year":[],"updated_date":"2026-01-08T20:05:33.558190","created_date":"2025-10-10T00:00:00"}
