{"id":"https://openalex.org/W2019075668","doi":"https://doi.org/10.1109/robot.2010.5509632","title":"A game-theoretic procedure for learning hierarchically structured strategies","display_name":"A game-theoretic procedure for learning hierarchically structured strategies","publication_year":2010,"publication_date":"2010-05-01","ids":{"openalex":"https://openalex.org/W2019075668","doi":"https://doi.org/10.1109/robot.2010.5509632","mag":"2019075668"},"language":"en","primary_location":{"id":"doi:10.1109/robot.2010.5509632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2010.5509632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Robotics and Automation","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/A5068297734","display_name":"Benjamin Rosman","orcid":"https://orcid.org/0000-0002-0284-4114"},"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":"Benjamin Rosman","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, UK","Sch. of Informatics, Univ. of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Sch. of Informatics, Univ. of 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, Edinburgh, UK","Sch. of Informatics, Univ. of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Sch. of Informatics, Univ. of 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":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"2977","last_page":"2983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9887999892234802,"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":0.9818999767303467,"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":0.7236068844795227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6361984014511108},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6074303388595581},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4997556209564209},{"id":"https://openalex.org/keywords/multiplicative-function","display_name":"Multiplicative function","score":0.4937926232814789},{"id":"https://openalex.org/keywords/navigability","display_name":"Navigability","score":0.4738357961177826},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11153817176818848},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10325184464454651}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7236068844795227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6361984014511108},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6074303388595581},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4997556209564209},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.4937926232814789},{"id":"https://openalex.org/C2778972660","wikidata":"https://www.wikidata.org/wiki/Q1666353","display_name":"Navigability","level":2,"score":0.4738357961177826},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11153817176818848},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10325184464454651},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/robot.2010.5509632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2010.5509632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Robotics and Automation","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.625.6723","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.625.6723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://homepages.inf.ed.ac.uk/s0896970/papers/icra10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1521785144","https://openalex.org/W1536443008","https://openalex.org/W1578630563","https://openalex.org/W1581660165","https://openalex.org/W1965878388","https://openalex.org/W1982486572","https://openalex.org/W1986014385","https://openalex.org/W1991387241","https://openalex.org/W1999874108","https://openalex.org/W2001685400","https://openalex.org/W2053680135","https://openalex.org/W2056864430","https://openalex.org/W2081203294","https://openalex.org/W2106887613","https://openalex.org/W2110221456","https://openalex.org/W2113023245","https://openalex.org/W2115524942","https://openalex.org/W2121863487","https://openalex.org/W2128103053","https://openalex.org/W2130726249","https://openalex.org/W2132580642","https://openalex.org/W2151834591","https://openalex.org/W2199385070","https://openalex.org/W2216069195","https://openalex.org/W2508573783","https://openalex.org/W4214717370","https://openalex.org/W6676728370","https://openalex.org/W6679903357"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3209574120","https://openalex.org/W3107602296","https://openalex.org/W4312192474","https://openalex.org/W4210805261","https://openalex.org/W4387297750"],"abstract_inverted_index":{"This":[0,16],"paper":[1],"addresses":[2],"the":[3,56,75,86,98,119],"problem":[4,43,76],"of":[5,22,28,41,58,65,77,95,110,118,126],"acquiring":[6],"a":[7,13,20,47,133,141],"hierarchically":[8],"structured":[9],"robotic":[10],"skill":[11],"in":[12,55,97,140],"nonstationary":[14],"environment.":[15],"is":[17,68,132],"achieved":[18],"through":[19,70],"combination":[21],"learning":[23,61,131],"primitive":[24],"strategies":[25,35],"from":[26,36,46],"observation":[27],"an":[29],"expert,":[30],"and":[31,108,130],"autonomously":[32],"synthesising":[33],"composite":[34],"that":[37,82,123],"basis.":[38],"Both":[39],"aspects":[40],"this":[42,66,83,124],"are":[44],"approached":[45],"game":[48],"theoretic":[49],"viewpoint,":[50],"building":[51],"on":[52],"prior":[53],"work":[54],"area":[57],"multiplicative":[59],"weights":[60],"algorithms.":[62],"The":[63],"utility":[64],"procedure":[67,84],"demonstrated":[69],"simulation":[71],"experiments":[72],"motivated":[73],"by":[74,115],"autonomous":[78,138],"driving.":[79],"We":[80,121],"show":[81],"allows":[85],"agent":[87],"to":[88,90,105],"come":[89],"terms":[91],"with":[92],"two":[93],"forms":[94],"uncertainty":[96],"world":[99],"-":[100],"continually":[101],"varying":[102],"goals":[103],"(due":[104],"oncoming":[106],"traffic)":[107],"nonstationarity":[109],"optimisation":[111],"criteria":[112],"(e.g.,":[113],"driven":[114],"changing":[116],"navigability":[117],"road).":[120],"argue":[122],"type":[125],"factored":[127],"task":[128],"specification":[129],"necessary":[134],"ingredient":[135],"for":[136],"robust":[137],"behaviour":[139],"\u201clarge-world\u201d":[142],"setting.":[143]},"counts_by_year":[{"year":2014,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
