{"id":"https://openalex.org/W4312247477","doi":"https://doi.org/10.1109/icdl53763.2022.9962187","title":"Getting Priorities Right: Intrinsic Motivation with Multi-Objective Reinforcement Learning","display_name":"Getting Priorities Right: Intrinsic Motivation with Multi-Objective Reinforcement Learning","publication_year":2022,"publication_date":"2022-09-12","ids":{"openalex":"https://openalex.org/W4312247477","doi":"https://doi.org/10.1109/icdl53763.2022.9962187"},"language":"en","primary_location":{"id":"doi:10.1109/icdl53763.2022.9962187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl53763.2022.9962187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-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/A5024600750","display_name":"Yusuf Al-Husaini","orcid":null},"institutions":[{"id":"https://openalex.org/I124261462","display_name":"Oxford Brookes University","ror":"https://ror.org/04v2twj65","country_code":"GB","type":"education","lineage":["https://openalex.org/I124261462"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yusuf Al-Husaini","raw_affiliation_strings":["Oxford Brookes University,School of Engineering, Computing and Mathematics,Oxford,UK","School of Engineering, Computing and Mathematics, Oxford Brookes University, Oxford, UK"],"affiliations":[{"raw_affiliation_string":"Oxford Brookes University,School of Engineering, Computing and Mathematics,Oxford,UK","institution_ids":["https://openalex.org/I124261462"]},{"raw_affiliation_string":"School of Engineering, Computing and Mathematics, Oxford Brookes University, Oxford, UK","institution_ids":["https://openalex.org/I124261462"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102882780","display_name":"Matthias Rolf","orcid":"https://orcid.org/0000-0003-0563-3264"},"institutions":[{"id":"https://openalex.org/I124261462","display_name":"Oxford Brookes University","ror":"https://ror.org/04v2twj65","country_code":"GB","type":"education","lineage":["https://openalex.org/I124261462"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Matthias Rolf","raw_affiliation_strings":["Oxford Brookes University,School of Engineering, Computing and Mathematics,Oxford,UK","School of Engineering, Computing and Mathematics, Oxford Brookes University, Oxford, UK"],"affiliations":[{"raw_affiliation_string":"Oxford Brookes University,School of Engineering, Computing and Mathematics,Oxford,UK","institution_ids":["https://openalex.org/I124261462"]},{"raw_affiliation_string":"School of Engineering, Computing and Mathematics, Oxford Brookes University, Oxford, UK","institution_ids":["https://openalex.org/I124261462"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5024600750"],"corresponding_institution_ids":["https://openalex.org/I124261462"],"apc_list":null,"apc_paid":null,"fwci":0.2283,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65038599,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"208","last_page":"214"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9858999848365784,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9858999848365784,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12786","display_name":"Innovation and Socioeconomic Development","score":0.9264000058174133,"subfield":{"id":"https://openalex.org/subfields/1403","display_name":"Business and International Management"},"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/curiosity","display_name":"Curiosity","score":0.9646768569946289},{"id":"https://openalex.org/keywords/sustenance","display_name":"Sustenance","score":0.952286958694458},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8652380704879761},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.7177491188049316},{"id":"https://openalex.org/keywords/intrinsic-motivation","display_name":"Intrinsic motivation","score":0.5642072558403015},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5271480083465576},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5231586694717407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35396885871887207},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2697860598564148},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.20446085929870605}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.9646768569946289},{"id":"https://openalex.org/C2776351498","wikidata":"https://www.wikidata.org/wiki/Q1434188","display_name":"Sustenance","level":2,"score":0.952286958694458},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8652380704879761},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.7177491188049316},{"id":"https://openalex.org/C2985564149","wikidata":"https://www.wikidata.org/wiki/Q644302","display_name":"Intrinsic motivation","level":2,"score":0.5642072558403015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5271480083465576},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5231586694717407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35396885871887207},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2697860598564148},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.20446085929870605},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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:10.1109/icdl53763.2022.9962187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl53763.2022.9962187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"},{"id":"pmh:tle:96c9b222-44f1-47a7-8290-cd7e20424522:afee126f-04b2-41a9-a6dd-b29b7c6c20ab:1","is_oa":false,"landing_page_url":"https://radar.brookes.ac.uk/radar/items/96c9b222-44f1-47a7-8290-cd7e20424522/1/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400541","display_name":"Radar (Oxford Brookes University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124261462","host_organization_name":"Oxford Brookes University","host_organization_lineage":["https://openalex.org/I124261462"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Getting priorities right : intrinsic motivation with multi-objective reinforcement learning","raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4390843312","https://openalex.org/W2742251305","https://openalex.org/W3188422189","https://openalex.org/W2794291817","https://openalex.org/W2296716661","https://openalex.org/W2031177956","https://openalex.org/W2236656409","https://openalex.org/W4283383718","https://openalex.org/W4210307370","https://openalex.org/W3094054656"],"abstract_inverted_index":{"Intrinsic":[0],"motivation":[1],"is":[2,14,102,115],"a":[3,22,57,79,126,152],"common":[4,131],"method":[5,134],"to":[6,17,72,78,104,117,141],"facilitate":[7],"exploration":[8],"in":[9,27,32,56,151],"reinforcement":[10,58,68,82,96],"learning":[11,20,59,69,83,97],"agents.":[12],"Curiosity":[13],"thereby":[15],"supposed":[16],"aid":[18],"the":[19,46,63,66,94,112,130,139,143],"of":[21,48,65,129],"primary":[23],"goal.":[24],"However,":[25],"indulging":[26],"curiosity":[28,89,147],"may":[29],"also":[30],"stand":[31],"conflict":[33],"with":[34,93],"more":[35],"urgent":[36],"or":[37],"essential":[38],"objectives":[39,150],"such":[40],"as":[41],"self-sustenance.":[42],"This":[43],"paper":[44],"addresses":[45],"problem":[47],"balancing":[49],"curiosity,":[50,74],"and":[51,75,119,138,148],"correctly":[52],"prioritising":[53],"other":[54,149],"needs":[55],"context.":[60],"We":[61],"demonstrate":[62,87,125],"use":[64],"multi-objective":[67,153],"framework":[70],"C-MORE":[71,101],"integrate":[73],"compare":[76],"results":[77],"standard":[80],"linear":[81,113,132],"integration.":[84],"Results":[85],"clearly":[86],"that":[88],"can":[90],"be":[91],"modelled":[92],"priority-objective":[95],"paradigm.":[98],"In":[99],"particular,":[100],"found":[103,116],"explore":[105],"robustly":[106],"while":[107],"maintaining":[108],"self-sustenance":[109],"objectives,":[110],"whereas":[111],"approach":[114],"over-explore":[118],"take":[120],"unnecessary":[121],"risks.":[122],"The":[123],"findings":[124],"significant":[127],"weakness":[128],"integration":[133],"for":[135],"intrinsic":[136],"motivation,":[137],"need":[140],"acknowledge":[142],"potential":[144],"conflicts":[145],"between":[146],"framework.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}