{"id":"https://openalex.org/W4296474732","doi":"https://doi.org/10.1109/cog51982.2022.9893550","title":"Task Relabelling for Multi-task Transfer using Successor Features","display_name":"Task Relabelling for Multi-task Transfer using Successor Features","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4296474732","doi":"https://doi.org/10.1109/cog51982.2022.9893550"},"language":"en","primary_location":{"id":"doi:10.1109/cog51982.2022.9893550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/84304/2/Perez-Liebana%20Task%20Relabelling%20for%20Multi-task%20Transfer%20using%20Successor%20Features%202022%20Accepted.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089072718","display_name":"Martin Balla","orcid":"https://orcid.org/0009-0009-2558-2100"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Martin Balla","raw_affiliation_strings":["Queen Mary University of London"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058274276","display_name":"Diego P\u00e9rez-Li\u00e9bana","orcid":"https://orcid.org/0000-0003-1958-0212"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Diego Perez-Liebana","raw_affiliation_strings":["Queen Mary University of London"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5089072718"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":0.1388,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55104527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"353","last_page":"360"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11749","display_name":"Iterative Learning Control Systems","score":0.9876999855041504,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/successor-cardinal","display_name":"Successor cardinal","score":0.8485070466995239},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7838042974472046},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7728132605552673},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06338578462600708}],"concepts":[{"id":"https://openalex.org/C75306776","wikidata":"https://www.wikidata.org/wiki/Q7632662","display_name":"Successor cardinal","level":2,"score":0.8485070466995239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7838042974472046},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7728132605552673},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06338578462600708},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cog51982.2022.9893550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog51982.2022.9893550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/84304","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/84304","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/84304/2/Perez-Liebana%20Task%20Relabelling%20for%20Multi-task%20Transfer%20using%20Successor%20Features%202022%20Accepted.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/84304","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/84304","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/84304/2/Perez-Liebana%20Task%20Relabelling%20for%20Multi-task%20Transfer%20using%20Successor%20Features%202022%20Accepted.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G2612525633","display_name":"EPSRC Centre for Doctoral Training in Intelligent Games & Game Intelligence (IGGI)","funder_award_id":"EP/L015846/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5861819490","display_name":null,"funder_award_id":"015846/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4296474732.pdf","grobid_xml":"https://content.openalex.org/works/W4296474732.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W567721252","https://openalex.org/W2056354534","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2440926996","https://openalex.org/W2480004914","https://openalex.org/W2736601468","https://openalex.org/W2897242117","https://openalex.org/W2953319434","https://openalex.org/W2971273232","https://openalex.org/W2982316857","https://openalex.org/W2994995984","https://openalex.org/W2997289589","https://openalex.org/W3072315125","https://openalex.org/W3094597259","https://openalex.org/W3131824536","https://openalex.org/W3213132814","https://openalex.org/W4286976660","https://openalex.org/W4289107543","https://openalex.org/W4297804343","https://openalex.org/W4300799055","https://openalex.org/W6616173779","https://openalex.org/W6716653466","https://openalex.org/W6718190810","https://openalex.org/W6721634521","https://openalex.org/W6740801417","https://openalex.org/W6741002519","https://openalex.org/W6756685538","https://openalex.org/W6764281707","https://openalex.org/W6767130282","https://openalex.org/W6791374197","https://openalex.org/W6801642480","https://openalex.org/W6803518980"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2473542051","https://openalex.org/W3123320268","https://openalex.org/W2994519609","https://openalex.org/W2726593096","https://openalex.org/W2054269721","https://openalex.org/W4235459050","https://openalex.org/W2767501615","https://openalex.org/W2390822611"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"has":[3],"been":[4],"very":[5],"successful":[6],"recently":[7],"with":[8,18],"various":[9,99],"works":[10,15],"on":[11,119],"complex":[12],"domains.":[13],"Most":[14],"are":[16,58],"concerned":[17],"learning":[19,55],"a":[20,51,81,127,136],"single":[21],"policy":[22],"that":[23,34,53,57,84],"solves":[24],"the":[25,32,36,39,95,120,132,143],"target":[26,100],"task,":[27],"but":[28],"is":[29,41,113],"fixed":[30],"in":[31,80],"sense":[33],"if":[35],"environment":[37,83],"changes":[38],"agent":[40],"unable":[42],"to":[43,45,61,98,109],"adapt":[44],"it.":[46],"Successor":[47],"Features":[48],"(SFs)":[49],"proposes":[50],"mechanism":[52],"allows":[54],"policies":[56],"not":[59],"tied":[60],"any":[62,78,116],"particular":[63],"reward":[64,79],"function.":[65],"In":[66],"this":[67],"work":[68],"we":[69,93,134],"investigate":[70],"how":[71,104],"SFs":[72,133],"may":[73],"be":[74],"pre-trained":[75],"without":[76,115],"observing":[77],"custom":[82],"features":[85],"resource":[86],"collection,":[87],"traps":[88],"and":[89,102],"crafting.":[90],"After":[91],"pre-training":[92],"expose":[94],"SF":[96,121],"agents":[97],"tasks":[101],"see":[103],"well":[105],"they":[106],"can":[107],"transfer":[108],"new":[110],"tasks.":[111],"Transferring":[112],"done":[114],"further":[117],"training":[118,131],"agents,":[122],"instead":[123],"just":[124],"by":[125],"providing":[126],"task":[128,137],"vector.":[129],"For":[130],"propose":[135],"relabelling":[138],"method":[139],"which":[140],"greatly":[141],"improves":[142],"agent\u2019s":[144],"performance.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}