{"id":"https://openalex.org/W3169971341","doi":"https://doi.org/10.3233/aic-230040","title":"Lifetime policy reuse and the importance of task capacity","display_name":"Lifetime policy reuse and the importance of task capacity","publication_year":2023,"publication_date":"2023-10-24","ids":{"openalex":"https://openalex.org/W3169971341","doi":"https://doi.org/10.3233/aic-230040","mag":"3169971341"},"language":"en","primary_location":{"id":"doi:10.3233/aic-230040","is_oa":true,"landing_page_url":"https://doi.org/10.3233/aic-230040","pdf_url":"https://content.iospress.com:443/download/ai-communications/aic230040?id=ai-communications%2Faic230040","source":{"id":"https://openalex.org/S176303223","display_name":"AI Communications","issn_l":"0921-7126","issn":["0921-7126","1875-8452"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AI Communications","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://content.iospress.com:443/download/ai-communications/aic230040?id=ai-communications%2Faic230040","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011218628","display_name":"David M. Bossens","orcid":"https://orcid.org/0000-0003-1924-5756"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"David M. Bossens","raw_affiliation_strings":["Maritime Engineering group, University of Southampton, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Maritime Engineering group, University of Southampton, United Kingdom","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039702362","display_name":"A.J. Sobey","orcid":"https://orcid.org/0000-0001-6880-8338"},"institutions":[{"id":"https://openalex.org/I125680101","display_name":"Turing Institute","ror":"https://ror.org/02x2mw849","country_code":"GB","type":"facility","lineage":["https://openalex.org/I125680101"]},{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]},{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adam J. Sobey","raw_affiliation_strings":["Marine and Maritime Group, The Alan Turing Institute, United Kingdom","Maritime Engineering group, University of Southampton, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Marine and Maritime Group, The Alan Turing Institute, United Kingdom","institution_ids":["https://openalex.org/I125680101","https://openalex.org/I4210128584"]},{"raw_affiliation_string":"Maritime Engineering group, University of Southampton, United Kingdom","institution_ids":["https://openalex.org/I43439940"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011218628"],"corresponding_institution_ids":["https://openalex.org/I43439940"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00190756,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"1","first_page":"115","last_page":"148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"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":0.9995999932289124,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.8691724538803101},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8608508110046387},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.7748428583145142},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.7125043869018555},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6986445188522339},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.525020182132721},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4536546766757965},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43489861488342285},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36498022079467773},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.07714274525642395}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8691724538803101},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8608508110046387},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.7748428583145142},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.7125043869018555},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6986445188522339},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.525020182132721},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4536546766757965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43489861488342285},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36498022079467773},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.07714274525642395},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"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},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3233/aic-230040","is_oa":true,"landing_page_url":"https://doi.org/10.3233/aic-230040","pdf_url":"https://content.iospress.com:443/download/ai-communications/aic230040?id=ai-communications%2Faic230040","source":{"id":"https://openalex.org/S176303223","display_name":"AI Communications","issn_l":"0921-7126","issn":["0921-7126","1875-8452"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AI Communications","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2106.01741","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.01741","pdf_url":"https://arxiv.org/pdf/2106.01741","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:eprints.soton.ac.uk:483617","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.soton.ac.uk/483617/1/manuscript_AICfinal.pdf","source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.3233/aic-230040","is_oa":true,"landing_page_url":"https://doi.org/10.3233/aic-230040","pdf_url":"https://content.iospress.com:443/download/ai-communications/aic230040?id=ai-communications%2Faic230040","source":{"id":"https://openalex.org/S176303223","display_name":"AI Communications","issn_l":"0921-7126","issn":["0921-7126","1875-8452"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AI Communications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320277","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543"},{"id":"https://openalex.org/F4320325699","display_name":"Lloyd's Register","ror":null},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3169971341.pdf","grobid_xml":"https://content.openalex.org/works/W3169971341.grobid-xml"},"referenced_works_count":84,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W21657860","https://openalex.org/W32403112","https://openalex.org/W92982764","https://openalex.org/W158722652","https://openalex.org/W567721252","https://openalex.org/W778742492","https://openalex.org/W1191599655","https://openalex.org/W1498436455","https://openalex.org/W1566538838","https://openalex.org/W1583380718","https://openalex.org/W1738827650","https://openalex.org/W1744884320","https://openalex.org/W1969074599","https://openalex.org/W2024450772","https://openalex.org/W2031727428","https://openalex.org/W2064675550","https://openalex.org/W2084376682","https://openalex.org/W2097381042","https://openalex.org/W2097498341","https://openalex.org/W2114451917","https://openalex.org/W2115599650","https://openalex.org/W2133458291","https://openalex.org/W2137509429","https://openalex.org/W2137825550","https://openalex.org/W2137983211","https://openalex.org/W2145339207","https://openalex.org/W2165698076","https://openalex.org/W2168405694","https://openalex.org/W2169743339","https://openalex.org/W2344023930","https://openalex.org/W2473930607","https://openalex.org/W2483550645","https://openalex.org/W2522489477","https://openalex.org/W2560647685","https://openalex.org/W2565989828","https://openalex.org/W2569829274","https://openalex.org/W2604268026","https://openalex.org/W2604763608","https://openalex.org/W2607273677","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2743151379","https://openalex.org/W2760355785","https://openalex.org/W2768629321","https://openalex.org/W2796979132","https://openalex.org/W2885550588","https://openalex.org/W2887671224","https://openalex.org/W2891287243","https://openalex.org/W2898290017","https://openalex.org/W2908064123","https://openalex.org/W2920215304","https://openalex.org/W2925093842","https://openalex.org/W2942369252","https://openalex.org/W2962715412","https://openalex.org/W2962747693","https://openalex.org/W2962808049","https://openalex.org/W2962938178","https://openalex.org/W2963065769","https://openalex.org/W2963178577","https://openalex.org/W2963775850","https://openalex.org/W2963959137","https://openalex.org/W2964048876","https://openalex.org/W2964118262","https://openalex.org/W2971266180","https://openalex.org/W2978320887","https://openalex.org/W2981344907","https://openalex.org/W3011697356","https://openalex.org/W3014201747","https://openalex.org/W3037645935","https://openalex.org/W3046814132","https://openalex.org/W3127461190","https://openalex.org/W4238284510","https://openalex.org/W4312744085","https://openalex.org/W6600292188","https://openalex.org/W6601926947","https://openalex.org/W6603474829","https://openalex.org/W6603695008","https://openalex.org/W6604208927","https://openalex.org/W6608490358","https://openalex.org/W6634537889","https://openalex.org/W6674600207","https://openalex.org/W6674664616","https://openalex.org/W6824051750"],"related_works":["https://openalex.org/W4289718052","https://openalex.org/W2164121020","https://openalex.org/W2145559838","https://openalex.org/W3116498279","https://openalex.org/W4287549553","https://openalex.org/W3183027292","https://openalex.org/W4310285384","https://openalex.org/W2794885965","https://openalex.org/W2104218666","https://openalex.org/W2959635497"],"abstract_inverted_index":{"A":[0],"long-standing":[1],"challenge":[2],"in":[3,16],"artificial":[4],"intelligence":[5],"is":[6],"lifelong":[7],"reinforcement":[8,33],"learning,":[9],"where":[10],"learners":[11],"are":[12],"given":[13],"many":[14,43,64],"tasks":[15,23,39,96],"sequence":[17],"and":[18,30,80,84,116,128],"must":[19],"transfer":[20],"knowledge":[21],"between":[22],"while":[24],"avoiding":[25],"catastrophic":[26],"forgetting.":[27],"Policy":[28,54,114],"reuse":[29,59],"other":[31],"multi-policy":[32],"learning":[34],"techniques":[35],"can":[36,100],"learn":[37],"multiple":[38],"but":[40],"may":[41],"generate":[42],"policies.":[44],"This":[45],"paper":[46],"presents":[47],"two":[48,104],"novel":[49],"contributions,":[50],"namely":[51],"1)":[52],"Lifetime":[53,113],"Reuse,":[55],"a":[56,68,75,89,98,129],"model-agnostic":[57],"policy":[58,78,82,99],"algorithm":[60],"that":[61,97],"avoids":[62],"generating":[63],"policies":[65,73],"by":[66],"optimising":[67],"fixed":[69],"number":[70,94],"of":[71,77,95,112,132],"near-optimal":[72],"through":[74],"combination":[76],"optimisation":[79],"adaptive":[81],"selection;":[83],"2)":[85],"the":[86,92,107,110],"task":[87,117],"capacity,":[88],"measure":[90],"for":[91],"maximal":[93],"accurately":[101],"solve.":[102],"Comparing":[103],"state-of-the-art":[105],"base-learners,":[106],"results":[108],"demonstrate":[109],"importance":[111],"Reuse":[115],"capacity":[118],"based":[119],"pre-selection":[120],"on":[121],"an":[122],"18-task":[123],"partially":[124],"observable":[125],"Pacman":[126],"domain":[127,131],"Cartpole":[130],"up":[133],"to":[134],"125":[135],"tasks.":[136]},"counts_by_year":[],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}
