{"id":"https://openalex.org/W4323244175","doi":"https://doi.org/10.5220/0011610300003393","title":"Deep W-Networks: Solving Multi-Objective Optimisation Problems with Deep Reinforcement Learning","display_name":"Deep W-Networks: Solving Multi-Objective Optimisation Problems with Deep Reinforcement Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4323244175","doi":"https://doi.org/10.5220/0011610300003393"},"language":"en","primary_location":{"id":"doi:10.5220/0011610300003393","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011610300003393","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0011610300003393","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054993601","display_name":"Jernej Hribar","orcid":"https://orcid.org/0000-0002-9446-7917"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Jernej Hribar","raw_affiliation_strings":["School of Computer Science and Statistics, Trinity College Dublin, Ireland, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Statistics, Trinity College Dublin, Ireland, --- Select a Country ---","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014060749","display_name":"Luke Hackett","orcid":null},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Luke Hackett","raw_affiliation_strings":["School of Computer Science and Statistics, Trinity College Dublin, Ireland, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Statistics, Trinity College Dublin, Ireland, --- Select a Country ---","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059738292","display_name":"Ivana Duspari\u0107","orcid":"https://orcid.org/0000-0003-0621-5400"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Ivana Dusparic","raw_affiliation_strings":["School of Computer Science and Statistics, Trinity College Dublin, Ireland, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Statistics, Trinity College Dublin, Ireland, --- Select a Country ---","institution_ids":["https://openalex.org/I205274468"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054993601"],"corresponding_institution_ids":["https://openalex.org/I205274468"],"apc_list":null,"apc_paid":null,"fwci":0.8058,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74400923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"17","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9976999759674072,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9976999759674072,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9667999744415283,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9573000073432922,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8780307173728943},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7701971530914307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5670983791351318},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4922620356082916},{"id":"https://openalex.org/keywords/competition","display_name":"Competition (biology)","score":0.4631219804286957},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.45728299021720886},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.43184155225753784},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.39828142523765564},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33142733573913574},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.191371351480484},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10816696286201477}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8780307173728943},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7701971530914307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5670983791351318},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4922620356082916},{"id":"https://openalex.org/C91306197","wikidata":"https://www.wikidata.org/wiki/Q45767","display_name":"Competition (biology)","level":2,"score":0.4631219804286957},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.45728299021720886},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.43184155225753784},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39828142523765564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33142733573913574},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.191371351480484},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10816696286201477},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0011610300003393","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011610300003393","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0011610300003393","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011610300003393","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Life below water","id":"https://metadata.un.org/sdg/14"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W24785488","https://openalex.org/W1553023101","https://openalex.org/W1987725948","https://openalex.org/W2012612381","https://openalex.org/W2112299196","https://openalex.org/W2128469511","https://openalex.org/W2201581102","https://openalex.org/W2220013079","https://openalex.org/W2530195778","https://openalex.org/W2790759781","https://openalex.org/W2795688094","https://openalex.org/W2950596486","https://openalex.org/W2951799221","https://openalex.org/W3083778362","https://openalex.org/W3088456218","https://openalex.org/W3201290909","https://openalex.org/W3217162497","https://openalex.org/W4298857966"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2043093291","https://openalex.org/W2101155126","https://openalex.org/W4380075502"],"abstract_inverted_index":{"In":[0],"this":[1,58],"paper,":[2],"we":[3,60,123],"build":[4],"on":[5],"advances":[6],"introduced":[7],"by":[8],"the":[9,16,33,43,82,106,113,116,126,131],"Deep":[10,84],"Q-Networks":[11],"(DQN)":[12],"approach":[13,87],"to":[14,24,50],"extend":[15],"multi-objective":[17,40,91,98],"tabular":[18,44,76],"Reinforcement":[19],"Learning":[20],"(RL)":[21],"algorithm":[22,29,128],"W-learning":[23,28],"large":[25,53],"state":[26,54],"spaces.":[27,55],"can":[30,129],"naturally":[31],"solve":[32],"competition":[34,107],"between":[35,108],"multiple":[36,109],"single":[37],"policies":[38,110],"in":[39,88,115,134],"environments.":[41,137],"However,":[42],"version":[45],"does":[46],"not":[47],"scale":[48],"well":[49],"environments":[51],"with":[52,64],"To":[56],"address":[57],"issue,":[59],"replace":[61],"underlying":[62],"Q-tables":[63],"DQN,":[65],"and":[66,97],"propose":[67],"an":[68],"addition":[69],"of":[70,118],"W-Networks,":[71],"as":[72],"a":[73,119],"replacement":[74],"for":[75],"weights":[77],"(W)":[78],"representations.":[79],"We":[80,101],"evaluate":[81],"resulting":[83],"W-Networks":[85],"(DWN)":[86],"two":[89],"widely-accepted":[90],"RL":[92],"benchmarks:":[93],"deep":[94],"sea":[95],"treasure":[96],"mountain":[99],"car.":[100],"show":[102],"that":[103,125],"DWN":[104],"solves":[105],"while":[111],"outperforming":[112],"baseline":[114],"form":[117],"DQN":[120],"solution.":[121],"Additionally,":[122],"demonstrate":[124],"proposed":[127],"find":[130],"Pareto":[132],"front":[133],"both":[135],"tested":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}