{"id":"https://openalex.org/W2101911972","doi":"https://doi.org/10.1109/robot.2010.5509717","title":"Apprenticeship learning via soft local homomorphisms","display_name":"Apprenticeship learning via soft local homomorphisms","publication_year":2010,"publication_date":"2010-05-01","ids":{"openalex":"https://openalex.org/W2101911972","doi":"https://doi.org/10.1109/robot.2010.5509717","mag":"2101911972"},"language":"en","primary_location":{"id":"doi:10.1109/robot.2010.5509717","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2010.5509717","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":"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/A5068615270","display_name":"Abdeslam Boularias","orcid":"https://orcid.org/0000-0002-5587-4560"},"institutions":[{"id":"https://openalex.org/I43406934","display_name":"Universit\u00e9 Laval","ror":"https://ror.org/04sjchr03","country_code":"CA","type":"education","lineage":["https://openalex.org/I43406934"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Abd Boularias","raw_affiliation_strings":["Computer Science and Software Engineering Department, Laval University, Quebec, G1V 0A6 Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Software Engineering Department, Laval University, Quebec, G1V 0A6 Canada","institution_ids":["https://openalex.org/I43406934"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002976111","display_name":"Brahim Chaib-draa","orcid":"https://orcid.org/0000-0001-7615-5154"},"institutions":[{"id":"https://openalex.org/I43406934","display_name":"Universit\u00e9 Laval","ror":"https://ror.org/04sjchr03","country_code":"CA","type":"education","lineage":["https://openalex.org/I43406934"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Brahim Chaib-draa","raw_affiliation_strings":["Computer Science and Software Engineering Department, Laval University, Quebec, G1V 0A6 Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Software Engineering Department, Laval University, Quebec, G1V 0A6 Canada","institution_ids":["https://openalex.org/I43406934"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3984,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.85345018,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2971","last_page":"2976"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.9980000257492065,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9943000078201294,"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/markov-decision-process","display_name":"Markov decision process","score":0.719658613204956},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6264087557792664},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5434894561767578},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5244141817092896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5093563795089722},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5060693621635437},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.490166038274765},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4709428548812866},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.46908751130104065},{"id":"https://openalex.org/keywords/homomorphism","display_name":"Homomorphism","score":0.44628989696502686},{"id":"https://openalex.org/keywords/apprenticeship","display_name":"Apprenticeship","score":0.4123563766479492},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4118499159812927},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23296067118644714},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.1223263144493103},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08984106779098511}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.719658613204956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6264087557792664},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5434894561767578},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5244141817092896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5093563795089722},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5060693621635437},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.490166038274765},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4709428548812866},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.46908751130104065},{"id":"https://openalex.org/C4042151","wikidata":"https://www.wikidata.org/wiki/Q215111","display_name":"Homomorphism","level":2,"score":0.44628989696502686},{"id":"https://openalex.org/C107806365","wikidata":"https://www.wikidata.org/wiki/Q253567","display_name":"Apprenticeship","level":2,"score":0.4123563766479492},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4118499159812927},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23296067118644714},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.1223263144493103},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08984106779098511},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/robot.2010.5509717","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2010.5509717","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:10.1.1.154.1557","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.154.1557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://damas.ift.ulaval.ca/publications/ICRA2010FinalVersion.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.163.2414","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.163.2414","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://damas.ift.ulaval.ca/~boularia/papers/ICRA10.pdf","raw_type":"text"},{"id":"pmh:oai:alma.01RUT_INST:11665239270004646","is_oa":false,"landing_page_url":"https://scholarship.libraries.rutgers.edu/esploro/outputs/conferenceProceeding/Apprenticeship-learning-via-soft-local-homomorphisms/991031666108004646","pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"},{"id":"pmh:oai:pure.mpg.de:item_1788789","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0013-C03A-5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2010 IEEE International Conference on Robotics and Automation (ICRA 2010)","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.75,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W24272225","https://openalex.org/W1540685400","https://openalex.org/W1564393562","https://openalex.org/W1975463331","https://openalex.org/W1999874108","https://openalex.org/W2061562262","https://openalex.org/W2097381042","https://openalex.org/W2102847492","https://openalex.org/W2116442740","https://openalex.org/W2161201865","https://openalex.org/W2167224731","https://openalex.org/W2950989964","https://openalex.org/W4241421703","https://openalex.org/W6600989536","https://openalex.org/W6632235069","https://openalex.org/W6677631742","https://openalex.org/W6684338915"],"related_works":["https://openalex.org/W2807018115","https://openalex.org/W4388236136","https://openalex.org/W2315999538","https://openalex.org/W4200250224","https://openalex.org/W2606546905","https://openalex.org/W2126560268","https://openalex.org/W2285658092","https://openalex.org/W187740018","https://openalex.org/W2482498454","https://openalex.org/W2162286586"],"abstract_inverted_index":{"Abstract":[0],"\u2014":[1],"We":[2],"consider":[3],"the":[4,10,36,39,60,67,70,73,78,82,86,95,116,123,134,141],"problem":[5,33],"of":[6,18,59,62,66,81,122,164],"apprenticeship":[7],"learning":[8],"when":[9,69],"expert\u2019s":[11,74,117],"demonstration":[12],"covers":[13],"only":[14,90],"a":[15,19,45,105,161],"small":[16,162],"part":[17],"large":[20],"state":[21,124],"space.":[22,125],"Inverse":[23],"Reinforcement":[24],"Learning":[25],"(IRL)":[26],"provides":[27],"an":[28,56,145],"efficient":[29],"solution":[30],"to":[31,103,114,119,139,156],"this":[32,99],"based":[34],"on":[35,53],"assumption":[37],"that":[38,77,151],"expert":[40,83],"is":[41,84,154],"optimally":[42],"acting":[43],"in":[44,112],"Markov":[46],"Decision":[47],"Process":[48],"(MDP).":[49],"However,":[50],"past":[51],"work":[52],"IRL":[54,146],"requires":[55],"accurate":[57],"estimate":[58],"frequency":[61],"encountering":[63],"each":[64],"feature":[65],"states":[68],"robot":[71],"follows":[72],"policy.":[75],"Given":[76],"complete":[79],"policy":[80,118,128],"unknown,":[85],"features":[87,142],"frequencies":[88,143],"can":[89,129],"be":[91,130],"empirically":[92],"estimated":[93],"from":[94,160],"demonstrated":[96],"trajectories.":[97],"In":[98],"paper,":[100],"we":[101],"propose":[102],"use":[104],"transfer":[106],"method,":[107],"known":[108],"as":[109,133],"soft":[110],"homomorphism,":[111],"order":[113],"generalize":[115],"unvisited":[120],"regions":[121],"The":[126],"generalized":[127],"used":[131],"either":[132],"robot\u2019s":[135],"final":[136],"policy,":[137],"or":[138],"calculate":[140],"within":[144],"algorithm.":[147],"Empirical":[148],"results":[149],"show":[150],"our":[152],"approach":[153],"able":[155],"learn":[157],"good":[158],"policies":[159],"number":[163],"demonstrations.":[165],"I.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}