{"id":"https://openalex.org/W7160956919","doi":"https://doi.org/10.1016/j.asoc.2026.115418","title":"Goal-set-conditioned dynamic multi-objective reinforcement learning algorithm for learning time-varying pareto optimal policies","display_name":"Goal-set-conditioned dynamic multi-objective reinforcement learning algorithm for learning time-varying pareto optimal policies","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W7160956919","doi":"https://doi.org/10.1016/j.asoc.2026.115418"},"language":"en","primary_location":{"id":"doi:10.1016/j.asoc.2026.115418","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.asoc.2026.115418","pdf_url":null,"source":{"id":"https://openalex.org/S140556538","display_name":"Applied Soft Computing","issn_l":"1568-4946","issn":["1568-4946","1872-9681"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Soft Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026063183","display_name":"Haofang Yu","orcid":"https://orcid.org/0000-0002-6441-2210"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Haofang Yu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6441-2210","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135920174","display_name":"Hongchuan Yang","orcid":"https://orcid.org/0000-0002-7323-2959"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongchuan Yang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7323-2959","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101307410","display_name":"Yanyan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanyan Huang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7331-9130","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026063183"],"corresponding_institution_ids":[],"apc_list":{"value":3350,"currency":"USD","value_usd":3350},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84672756,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"200","issue":null,"first_page":"115418","last_page":"115418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.6495000123977661,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.6495000123977661,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2037999927997589,"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":0.04580000042915344,"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":0.7696999907493591},{"id":"https://openalex.org/keywords/pareto-optimal","display_name":"Pareto optimal","score":0.43860000371932983},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.4300999939441681},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.35040000081062317},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.33550000190734863},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.3077999949455261},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.3068000078201294}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7696999907493591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7336000204086304},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5241000056266785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.461899995803833},{"id":"https://openalex.org/C2986314615","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto optimal","level":3,"score":0.43860000371932983},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4235000014305115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36559998989105225},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.3077999949455261},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.30630001425743103},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C17061570","wikidata":"https://www.wikidata.org/wiki/Q7960888","display_name":"Wake-sleep algorithm","level":4,"score":0.2685999870300293}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.asoc.2026.115418","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.asoc.2026.115418","pdf_url":null,"source":{"id":"https://openalex.org/S140556538","display_name":"Applied Soft Computing","issn_l":"1568-4946","issn":["1568-4946","1872-9681"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Soft Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2058192020","https://openalex.org/W2102660061","https://openalex.org/W2142844925","https://openalex.org/W2143381319","https://openalex.org/W2343489328","https://openalex.org/W2395579298","https://openalex.org/W2583496274","https://openalex.org/W2601733549","https://openalex.org/W2945687849","https://openalex.org/W2971388538","https://openalex.org/W3084357507","https://openalex.org/W3135798356","https://openalex.org/W3138512992","https://openalex.org/W4285009743","https://openalex.org/W4287266177","https://openalex.org/W4308571246","https://openalex.org/W4328102232","https://openalex.org/W4367311517","https://openalex.org/W4367597515","https://openalex.org/W4393253095","https://openalex.org/W7133245600"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-05-26T06:15:08.310788","created_date":"2026-05-13T00:00:00"}