{"id":"https://openalex.org/W2968212703","doi":"https://doi.org/10.1177/1059712319869313","title":"A robust policy bootstrapping algorithm for multi-objective reinforcement learning in non-stationary environments","display_name":"A robust policy bootstrapping algorithm for multi-objective reinforcement learning in non-stationary environments","publication_year":2019,"publication_date":"2019-08-15","ids":{"openalex":"https://openalex.org/W2968212703","doi":"https://doi.org/10.1177/1059712319869313","mag":"2968212703"},"language":"en","primary_location":{"id":"doi:10.1177/1059712319869313","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1059712319869313","pdf_url":null,"source":{"id":"https://openalex.org/S183337005","display_name":"Adaptive Behavior","issn_l":"1059-7123","issn":["1059-7123","1741-2633"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptive Behavior","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://unsworks.unsw.edu.au/bitstreams/92e8098f-0df1-4f31-975d-425803038db7/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066773785","display_name":"Sherif Abdelfattah","orcid":null},"institutions":[{"id":"https://openalex.org/I4394709116","display_name":"UNSW Canberra","ror":"https://ror.org/0125wpx05","country_code":null,"type":"education","lineage":["https://openalex.org/I31746571","https://openalex.org/I4394709116"]},{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Sherif Abdelfattah","raw_affiliation_strings":["School of Engineering and Information Technology, UNSW Canberra, Canberra, ACT, Australia"],"affiliations":[{"raw_affiliation_string":"School of Engineering and Information Technology, UNSW Canberra, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I4394709116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047705901","display_name":"Kathryn Kasmarik","orcid":"https://orcid.org/0000-0001-7187-0474"},"institutions":[{"id":"https://openalex.org/I4394709116","display_name":"UNSW Canberra","ror":"https://ror.org/0125wpx05","country_code":null,"type":"education","lineage":["https://openalex.org/I31746571","https://openalex.org/I4394709116"]},{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kathryn Kasmarik","raw_affiliation_strings":["School of Engineering and Information Technology, UNSW Canberra, Canberra, ACT, Australia"],"affiliations":[{"raw_affiliation_string":"School of Engineering and Information Technology, UNSW Canberra, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I4394709116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075234257","display_name":"Jiankun Hu","orcid":"https://orcid.org/0000-0003-0230-1432"},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]},{"id":"https://openalex.org/I4394709116","display_name":"UNSW Canberra","ror":"https://ror.org/0125wpx05","country_code":null,"type":"education","lineage":["https://openalex.org/I31746571","https://openalex.org/I4394709116"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jiankun Hu","raw_affiliation_strings":["School of Engineering and Information Technology, UNSW Canberra, Canberra, ACT, Australia"],"affiliations":[{"raw_affiliation_string":"School of Engineering and Information Technology, UNSW Canberra, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I4394709116"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066773785"],"corresponding_institution_ids":["https://openalex.org/I188329596","https://openalex.org/I4394709116"],"apc_list":null,"apc_paid":null,"fwci":0.1447,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.57656844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"28","issue":"4","first_page":"273","last_page":"292"},"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9984999895095825,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9933000206947327,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8405551910400391},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7298713326454163},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7034305334091187},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5334729552268982},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4958396852016449},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4773830771446228},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.47237637639045715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45100489258766174},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4398255944252014},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4301295876502991},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4060012996196747},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3513834476470947},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2657286524772644},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18988081812858582}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8405551910400391},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7298713326454163},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7034305334091187},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5334729552268982},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4958396852016449},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4773830771446228},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.47237637639045715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45100489258766174},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4398255944252014},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4301295876502991},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4060012996196747},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3513834476470947},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2657286524772644},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18988081812858582},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1177/1059712319869313","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1059712319869313","pdf_url":null,"source":{"id":"https://openalex.org/S183337005","display_name":"Adaptive Behavior","issn_l":"1059-7123","issn":["1059-7123","1741-2633"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptive Behavior","raw_type":"journal-article"},{"id":"pmh:oai:unsworks.library.unsw.edu.au:1959.4/unsworks_60153","is_oa":true,"landing_page_url":"http://hdl.handle.net/1959.4/unsworks_60153","pdf_url":"https://unsworks.unsw.edu.au/bitstreams/92e8098f-0df1-4f31-975d-425803038db7/download","source":{"id":"https://openalex.org/S4306401737","display_name":"UNSWorks (University of New South Wales, Sydney, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40053085","host_organization_name":"Australian Defence Force Academy","host_organization_lineage":["https://openalex.org/I40053085"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Adaptive Behavior, 28, 4, 273-292","raw_type":"http://purl.org/coar/resource_type/c_6501"}],"best_oa_location":{"id":"pmh:oai:unsworks.library.unsw.edu.au:1959.4/unsworks_60153","is_oa":true,"landing_page_url":"http://hdl.handle.net/1959.4/unsworks_60153","pdf_url":"https://unsworks.unsw.edu.au/bitstreams/92e8098f-0df1-4f31-975d-425803038db7/download","source":{"id":"https://openalex.org/S4306401737","display_name":"UNSWorks (University of New South Wales, Sydney, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40053085","host_organization_name":"Australian Defence Force Academy","host_organization_lineage":["https://openalex.org/I40053085"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Adaptive Behavior, 28, 4, 273-292","raw_type":"http://purl.org/coar/resource_type/c_6501"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.800000011920929}],"awards":[],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2968212703.pdf","grobid_xml":"https://content.openalex.org/works/W2968212703.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W122021961","https://openalex.org/W194486498","https://openalex.org/W291243768","https://openalex.org/W641771830","https://openalex.org/W1482041209","https://openalex.org/W1506085041","https://openalex.org/W1518318201","https://openalex.org/W1518931405","https://openalex.org/W1519783625","https://openalex.org/W1942501264","https://openalex.org/W1967053981","https://openalex.org/W1967102908","https://openalex.org/W1987725948","https://openalex.org/W2004883573","https://openalex.org/W2005437559","https://openalex.org/W2012612381","https://openalex.org/W2032100464","https://openalex.org/W2032950725","https://openalex.org/W2046211159","https://openalex.org/W2060846151","https://openalex.org/W2102660061","https://openalex.org/W2117428849","https://openalex.org/W2132886043","https://openalex.org/W2145339207","https://openalex.org/W2149726897","https://openalex.org/W2154023516","https://openalex.org/W2155027007","https://openalex.org/W2166364496","https://openalex.org/W2182714085","https://openalex.org/W2198098822","https://openalex.org/W2257979135","https://openalex.org/W2294971140","https://openalex.org/W2503173364","https://openalex.org/W2559655401","https://openalex.org/W2897714018","https://openalex.org/W4211221179","https://openalex.org/W4212780904","https://openalex.org/W4214717370","https://openalex.org/W4233696721","https://openalex.org/W6635327058","https://openalex.org/W6684470913","https://openalex.org/W6691518582"],"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":{"Multi-objective":[0,25],"Markov":[1,20],"decision":[2,15],"processes":[3],"are":[4],"a":[5,75,88,114,124],"special":[6],"kind":[7,31],"of":[8,22,32,47,53,78,128],"multi-objective":[9,41,116,145],"optimization":[10,42,66,90],"problem":[11,33],"that":[12,68,80,92,120,156],"involves":[13],"sequential":[14],"making":[16],"while":[17,99,168],"satisfying":[18],"the":[19,36,51,59,83,95,101,105,139,157,162],"property":[21],"stochastic":[23],"processes.":[24],"reinforcement":[26,37,117,146],"learning":[27,38,118,147],"methods":[28,49],"address":[29],"this":[30],"by":[34],"fusing":[35],"paradigm":[39],"with":[40,142],"techniques.":[43],"One":[44],"major":[45],"drawback":[46],"these":[48],"is":[50,62],"lack":[52],"adaptability":[54],"to":[55,73],"non-stationary":[56,135,152,166],"dynamics":[57],"in":[58,71,108,130,134,149,165,172],"environment.":[60],"This":[61,85],"because":[63],"they":[64],"adopt":[65],"procedures":[67],"assume":[69],"stationarity":[70],"order":[72],"evolve":[74,94,123],"coverage":[76,97,126],"set":[77,98,127],"policies":[79,129],"can":[81,93,121],"solve":[82],"problem.":[84],"article":[86],"introduces":[87],"developmental":[89],"approach":[91],"policy":[96],"exploring":[100],"preference":[102],"space":[103],"over":[104],"defined":[106],"objectives":[107],"an":[109,131],"online":[110,132],"manner.":[111],"We":[112,137],"propose":[113],"novel":[115],"algorithm":[119,141,159],"robustly":[122],"convex":[125],"manner":[133],"environments.":[136,153,174],"compare":[138],"proposed":[140,158],"two":[143],"state-of-the-art":[144],"algorithms":[148,164],"stationary":[150,173],"and":[151],"Results":[154],"showed":[155],"significantly":[160],"outperforms":[161],"existing":[163],"environments":[167],"achieving":[169],"comparable":[170],"results":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}