{"id":"https://openalex.org/W2044843771","doi":"https://doi.org/10.1109/iros.2013.6696523","title":"Lifelong transfer learning with an option hierarchy","display_name":"Lifelong transfer learning with an option hierarchy","publication_year":2013,"publication_date":"2013-11-01","ids":{"openalex":"https://openalex.org/W2044843771","doi":"https://doi.org/10.1109/iros.2013.6696523","mag":"2044843771"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2013.6696523","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2013.6696523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},"type":"conference-paper","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/A5021151663","display_name":"Majd Hawasly","orcid":"https://orcid.org/0000-0003-1823-5580"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Majd Hawasly","raw_affiliation_strings":["School of Informatics, University of Edinburgh, United Kingdom","[Sch. of Inf., Univ. of Edinburgh, Edinburgh, UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"[Sch. of Inf., Univ. of Edinburgh, Edinburgh, UK]","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071122608","display_name":"Subramanian Ramamoorthy","orcid":"https://orcid.org/0000-0002-6300-5103"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Subramanian Ramamoorthy","raw_affiliation_strings":["School of Informatics, University of Edinburgh, United Kingdom","[Sch. of Inf., Univ. of Edinburgh, Edinburgh, UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"[Sch. of Inf., Univ. of Edinburgh, Edinburgh, UK]","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"1341","last_page":"1346"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T10462","display_name":"Reinforcement Learning in Robotics","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9965999722480774,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9860000014305115,"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":0.7775264382362366},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6654993295669556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6406859159469604},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6275997757911682},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6164671182632446},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.6005587577819824},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5271216034889221},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.51080322265625},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.507604718208313},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.47000983357429504},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4623355567455292},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4529139995574951},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.42982128262519836},{"id":"https://openalex.org/keywords/lifelong-learning","display_name":"Lifelong learning","score":0.41770797967910767},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37633007764816284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7775264382362366},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6654993295669556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6406859159469604},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6275997757911682},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6164671182632446},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.6005587577819824},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5271216034889221},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.51080322265625},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.507604718208313},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.47000983357429504},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4623355567455292},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4529139995574951},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42982128262519836},{"id":"https://openalex.org/C108771440","wikidata":"https://www.wikidata.org/wiki/Q368475","display_name":"Lifelong learning","level":2,"score":0.41770797967910767},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37633007764816284},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2013.6696523","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2013.6696523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1492014007","https://openalex.org/W1510402218","https://openalex.org/W1523801836","https://openalex.org/W1536990779","https://openalex.org/W1556824961","https://openalex.org/W1592847719","https://openalex.org/W1598748993","https://openalex.org/W1968768508","https://openalex.org/W2031727428","https://openalex.org/W2049633694","https://openalex.org/W2096195880","https://openalex.org/W2097381042","https://openalex.org/W2104641222","https://openalex.org/W2109910161","https://openalex.org/W2114199765","https://openalex.org/W2114451917","https://openalex.org/W2132057084","https://openalex.org/W2133853511","https://openalex.org/W2145983895","https://openalex.org/W2168640731","https://openalex.org/W2169743339","https://openalex.org/W2172131460","https://openalex.org/W2188752309","https://openalex.org/W4249441547","https://openalex.org/W6629461247","https://openalex.org/W6632315374","https://openalex.org/W6642630624","https://openalex.org/W6674600207","https://openalex.org/W6676772908","https://openalex.org/W6676824205","https://openalex.org/W6679792627","https://openalex.org/W6684863604","https://openalex.org/W6685218902","https://openalex.org/W6687081237"],"related_works":["https://openalex.org/W2364105709","https://openalex.org/W2384383462","https://openalex.org/W2380954666","https://openalex.org/W422428167","https://openalex.org/W1981922029","https://openalex.org/W2037025106","https://openalex.org/W2499777278","https://openalex.org/W2391851613","https://openalex.org/W1485190762","https://openalex.org/W4372778609"],"abstract_inverted_index":{"Many":[0],"applications":[1],"require":[2],"autonomous":[3],"agents":[4],"to":[5,9,61,73,82,99],"achieve":[6],"quick":[7],"responses":[8],"task":[10,123],"instances":[11],"drawn":[12],"from":[13,93,115],"a":[14,28,43,69,153],"rich":[15],"family":[16],"of":[17,56,145,168],"qualitatively-related":[18],"tasks.":[19],"We":[20,41,67],"address":[21],"the":[22,25,33,54,118,139,160],"setting":[23],"where":[24,47],"tasks":[26],"share":[27],"state-action":[29],"space":[30,78],"and":[31,109,134,157],"have":[32],"same":[34],"qualitative":[35],"objective":[36],"but":[37],"differ":[38],"in":[39,50,53,64,76,85,129,152,159],"dynamics.":[40],"adopt":[42],"transfer":[44],"learning":[45,63,132,136],"approach":[46],"common":[48,81],"structure":[49],"previously-learnt":[51,94],"policies,":[52],"form":[55],"shared":[57],"subtasks,":[58],"is":[59,148],"exploited":[60],"accelerate":[62],"subsequent":[65],"ones.":[66],"use":[68],"probabilistic":[70],"mixture":[71,119],"model":[72],"describe":[74],"regions":[75],"state":[77],"which":[79],"are":[80,97,105,112,127],"successful":[83],"trajectories":[84],"different":[86,169],"instances.":[87],"Then,":[88],"we":[89],"extract":[90],"policy":[91,103,141],"fragments":[92,104],"policies":[95],"that":[96],"specialised":[98],"these":[100,125],"regions.":[101],"These":[102],"options,":[106],"whose":[107],"initiation":[108],"termination":[110],"sets":[111],"automatically":[113],"extracted":[114],"data":[116],"by":[117],"model.":[120],"In":[121],"novel":[122],"instances,":[124],"options":[126],"used":[128],"an":[130],"SMDP":[131],"process":[133],"option":[135],"repeats":[137],"over":[138],"resulting":[140],"library.":[142],"The":[143],"utility":[144],"this":[146],"method":[147],"demonstrated":[149],"through":[150],"experiments":[151],"standard":[154],"navigation":[155],"environment":[156],"then":[158],"RoboCup":[161],"simulated":[162],"soccer":[163],"domain":[164],"with":[165],"opponent":[166],"teams":[167],"skill.":[170]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
