{"id":"https://openalex.org/W4389665399","doi":"https://doi.org/10.1109/iros55552.2023.10341403","title":"Imitation-Guided Multimodal Policy Generation from Behaviourally Diverse Demonstrations","display_name":"Imitation-Guided Multimodal Policy Generation from Behaviourally Diverse Demonstrations","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389665399","doi":"https://doi.org/10.1109/iros55552.2023.10341403"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341403","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iros55552.2023.10341403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.aalto.fi/en/publications/172473d5-1b84-494f-acad-7eba3436677a","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004594052","display_name":"Shibei Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shibei Zhu","raw_affiliation_strings":["Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072492839","display_name":"Rituraj Kaushik","orcid":"https://orcid.org/0000-0003-2598-8804"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Rituraj Kaushik","raw_affiliation_strings":["Aalto University,Department of Electrical Engineering and Automation,Finland","Department of Electrical Engineering and Automation, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Electrical Engineering and Automation,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Electrical Engineering and Automation, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018305257","display_name":"Samuel Kaski","orcid":"https://orcid.org/0000-0003-1925-9154"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Samuel Kaski","raw_affiliation_strings":["Department of Computer Science","Department of Computer Science, University of Manchester, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science, University of Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080940147","display_name":"Ville Kyrki","orcid":"https://orcid.org/0000-0002-5230-5549"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ville Kyrki","raw_affiliation_strings":["Aalto University,Department of Electrical Engineering and Automation,Finland","Department of Electrical Engineering and Automation, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Electrical Engineering and Automation,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Electrical Engineering and Automation, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1753579,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":null,"first_page":"1675","last_page":"1682"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9825000166893005,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9711999893188477,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7860735654830933},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.7251229286193848},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.720669150352478},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.605217695236206},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.601471483707428},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5730893611907959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5653418302536011},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5615473389625549},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.559400737285614},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5109974145889282},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.44725966453552246},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43215489387512207},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3413376212120056},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10519438982009888},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07154646515846252}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7860735654830933},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7251229286193848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.720669150352478},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.605217695236206},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.601471483707428},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5730893611907959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5653418302536011},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5615473389625549},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.559400737285614},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5109974145889282},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.44725966453552246},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43215489387512207},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3413376212120056},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10519438982009888},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07154646515846252},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iros55552.2023.10341403","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iros55552.2023.10341403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/24eee497-4fe5-492b-85dc-4f985a49db0a","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/24eee497-4fe5-492b-85dc-4f985a49db0a","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Zhu, S, Kaushik, R, Kaski, S & Kyrki, V 2023, Imitation-guided Multimodal Policy Generation from Behaviourally Diverse Demonstrations. in 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, pp. 1675-1682, IEEE/RSJ International Conference on Intelligent Robots and Systems , United States, 1/10/23. https://doi.org/10.1109/IROS55552.2023.10341403","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/125764","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/172473d5-1b84-494f-acad-7eba3436677a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/125764","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/172473d5-1b84-494f-acad-7eba3436677a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W758372786","https://openalex.org/W1617122252","https://openalex.org/W1738827650","https://openalex.org/W2000514530","https://openalex.org/W2139612737","https://openalex.org/W2169498096","https://openalex.org/W2471883051","https://openalex.org/W2474718355","https://openalex.org/W2539402368","https://openalex.org/W2560674852","https://openalex.org/W2593390416","https://openalex.org/W2606327391","https://openalex.org/W2617539464","https://openalex.org/W2739858255","https://openalex.org/W2741122588","https://openalex.org/W2962687375","https://openalex.org/W2962787969","https://openalex.org/W2963099939","https://openalex.org/W2963277051","https://openalex.org/W2963411833","https://openalex.org/W2963684088","https://openalex.org/W2963713397","https://openalex.org/W2968340082","https://openalex.org/W2971870892","https://openalex.org/W2985060393","https://openalex.org/W3001500946","https://openalex.org/W3089538634","https://openalex.org/W3182474098","https://openalex.org/W3188817182","https://openalex.org/W4283395244","https://openalex.org/W4283462717","https://openalex.org/W4285233190","https://openalex.org/W4320013936","https://openalex.org/W6622219343","https://openalex.org/W6674887261","https://openalex.org/W6685352114","https://openalex.org/W6685962732","https://openalex.org/W6716193690","https://openalex.org/W6718092244","https://openalex.org/W6738027021","https://openalex.org/W6739193204","https://openalex.org/W6742461812","https://openalex.org/W6751526458","https://openalex.org/W6762687050","https://openalex.org/W6763078103","https://openalex.org/W6769977606","https://openalex.org/W6770722459","https://openalex.org/W6783268431","https://openalex.org/W6786031796","https://openalex.org/W6838833932","https://openalex.org/W6839095744"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2778153218","https://openalex.org/W1531601525","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"Learning":[0],"policies":[1,172],"from":[2,71,83,120],"multiple":[3],"demonstrators":[4],"is":[5,128],"often":[6,38],"difficult":[7],"because":[8],"different":[9],"individuals":[10],"perform":[11,160],"the":[12,24,48,51,66,97,100,116,136,139,147,166],"same":[13],"task":[14,137],"differently":[15],"due":[16],"to":[17,31,40,46,64,95,122,131,134,144,170,178],"hidden":[18],"factors":[19],"such":[20,124],"as":[21,138],"preferences.":[22],"In":[23,54,150],"context":[25],"of":[26,75],"policy":[27,35,68,163,181],"learning,":[28],"this":[29,55,107],"leads":[30],"multimodal":[32,67],"policies.":[33],"Existing":[34],"learning":[36,62,69],"methods":[37],"converge":[39],"a":[41,72,91,111,161,180,184],"single":[42],"solution":[43,52,93,168],"mode,":[44],"failing":[45],"capture":[47,96],"diversity":[49],"in":[50,99,165],"space.":[53,125],"paper,":[56],"we":[57,79,109,152,158],"introduce":[58],"an":[59,87],"imitation-guided":[60],"reinforcement":[61],"framework":[63],"solve":[65,135],"problem":[70],"limited":[73],"number":[74],"state-only":[76],"demonstrations.":[77,105,149],"Then,":[78],"propose":[80],"LfBD":[81],"(Learning":[82],"Behaviourally":[84],"diverse":[85],"Demonstration),":[86],"algorithm":[88],"that":[89,154,173,182],"builds":[90],"parameterised":[92],"space":[94,102,169],"variability":[98],"behaviour":[101],"defined":[103],"by":[104],"To":[106],"end,":[108],"define":[110,123],"projection":[112],"function":[113],"based":[114],"on":[115],"state":[117],"density":[118],"distributions":[119],"demonstrations":[121],"Our":[126],"goal":[127],"not":[129],"only":[130],"learn":[132],"how":[133],"human":[140],"demonstrator":[141],"but":[142],"also":[143],"extrapolate":[145],"beyond":[146],"provided":[148],"addition,":[151],"show":[153],"with":[155],"our":[156],"method,":[157],"can":[159],"post-hoc":[162],"search":[164],"built":[167],"recover":[171],"satisfy":[174],"specific":[175],"constraints":[176],"or":[177],"find":[179],"matches":[183],"given":[185],"(state-only)":[186],"behaviour.":[187]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}