{"id":"https://openalex.org/W4285231577","doi":"https://doi.org/10.1109/lra.2022.3182100","title":"Interactive Reinforcement Learning With Bayesian Fusion of Multimodal Advice","display_name":"Interactive Reinforcement Learning With Bayesian Fusion of Multimodal Advice","publication_year":2022,"publication_date":"2022-06-13","ids":{"openalex":"https://openalex.org/W4285231577","doi":"https://doi.org/10.1109/lra.2022.3182100"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2022.3182100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3182100","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5068233406","display_name":"Susanne Trick","orcid":"https://orcid.org/0000-0001-5790-5060"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Susanne Trick","raw_affiliation_strings":["Centre for Cognitive Science and Psychology of Information Processing, Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5790-5060","affiliations":[{"raw_affiliation_string":"Centre for Cognitive Science and Psychology of Information Processing, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102741270","display_name":"Franziska Herbert","orcid":"https://orcid.org/0000-0003-4191-9366"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Franziska Herbert","raw_affiliation_strings":["Centre for Cognitive Science, Technical University of Darmstadt, Darmstadt, Germany","Intelligent Autonomous Systems, Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4191-9366","affiliations":[{"raw_affiliation_string":"Centre for Cognitive Science, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Intelligent Autonomous Systems, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015277967","display_name":"Constantin A. Rothkopf","orcid":"https://orcid.org/0000-0002-5636-0801"},"institutions":[{"id":"https://openalex.org/I114090438","display_name":"Goethe University Frankfurt","ror":"https://ror.org/04cvxnb49","country_code":"DE","type":"education","lineage":["https://openalex.org/I114090438"]},{"id":"https://openalex.org/I2801628138","display_name":"Frankfurt Institute for Advanced Studies","ror":"https://ror.org/05vmv8m79","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2801628138"]},{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Constantin A. Rothkopf","raw_affiliation_strings":["Centre for Cognitive Science and Psychology of Information Processing, Technical University of Darmstadt, Darmstadt, Germany","Frankfurt Institute for Advanced Studies, Goethe University Frankfurt, Frankfurt, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5636-0801","affiliations":[{"raw_affiliation_string":"Centre for Cognitive Science and Psychology of Information Processing, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Frankfurt Institute for Advanced Studies, Goethe University Frankfurt, Frankfurt, Germany","institution_ids":["https://openalex.org/I2801628138","https://openalex.org/I114090438"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063353075","display_name":"Dorothea Koert","orcid":"https://orcid.org/0000-0002-3571-6848"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dorothea Koert","raw_affiliation_strings":["Centre for Cognitive Science, Technical University of Darmstadt, Darmstadt, Germany","Intelligent Autonomous Systems, Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3571-6848","affiliations":[{"raw_affiliation_string":"Centre for Cognitive Science, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Intelligent Autonomous Systems, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068233406"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":1.6648,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.86316249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"7","issue":"3","first_page":"7558","last_page":"7565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"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":0.9977999925613403,"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/T12031","display_name":"Speech and dialogue systems","score":0.9918000102043152,"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":0.9896000027656555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7491662502288818},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6821458339691162},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6264772415161133},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5924245715141296},{"id":"https://openalex.org/keywords/advice","display_name":"Advice (programming)","score":0.511655867099762},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5090546011924744},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4910614490509033},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.490667462348938},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4482010304927826},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4383925795555115},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43466681241989136},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08974045515060425}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7491662502288818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6821458339691162},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6264772415161133},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5924245715141296},{"id":"https://openalex.org/C2779955035","wikidata":"https://www.wikidata.org/wiki/Q4686785","display_name":"Advice (programming)","level":2,"score":0.511655867099762},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5090546011924744},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4910614490509033},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.490667462348938},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4482010304927826},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4383925795555115},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43466681241989136},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08974045515060425},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2022.3182100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3182100","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:134266","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/134266/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Artikel"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1484536156","https://openalex.org/W1484600405","https://openalex.org/W1655191480","https://openalex.org/W1655830068","https://openalex.org/W1988520084","https://openalex.org/W2104308387","https://openalex.org/W2107574152","https://openalex.org/W2110064869","https://openalex.org/W2111715140","https://openalex.org/W2124267516","https://openalex.org/W2132504164","https://openalex.org/W2140584963","https://openalex.org/W2143926884","https://openalex.org/W2151074445","https://openalex.org/W2419349576","https://openalex.org/W2512044115","https://openalex.org/W2560862806","https://openalex.org/W2565110810","https://openalex.org/W2570651606","https://openalex.org/W2765347007","https://openalex.org/W2883750587","https://openalex.org/W2894609524","https://openalex.org/W2962730651","https://openalex.org/W3003620459","https://openalex.org/W3022194887","https://openalex.org/W3039772337","https://openalex.org/W4233216703","https://openalex.org/W4392307962","https://openalex.org/W6607978175","https://openalex.org/W6717094648","https://openalex.org/W6745159674","https://openalex.org/W6747778779","https://openalex.org/W6753814467","https://openalex.org/W6774122581"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Interactive":[0],"Reinforcement":[1,14],"Learning":[2,15],"(IRL)":[3],"has":[4],"shown":[5],"promising":[6],"results":[7],"in":[8,114,119],"decreasing":[9],"the":[10,25,88,111,115,143,161],"learning":[11],"times":[12],"of":[13,27,46,160],"algorithms":[16],"by":[17],"incorporating":[18],"human":[19,59],"feedback":[20,29],"and":[21,34,43,83,108,125],"advice.":[22],"In":[23,49,150],"particular,":[24,151],"integration":[26],"multimodal":[28,148],"channels":[30],"such":[31],"as":[32],"speech":[33],"gestures":[35],"into":[36,64],"IRL":[37,65],"systems":[38],"can":[39],"enable":[40],"more":[41,156],"versatile":[42],"natural":[44],"interaction":[45,130],"everyday":[47],"users.":[48],"this":[50],"letter,":[51],"we":[52,71],"propose":[53],"a":[54,79,120,127,133],"novel":[55,153],"approach":[56,104,146,154],"to":[57],"integrate":[58],"advice":[60,69],"from":[61],"multiple":[62],"modalities":[63],"algorithms.":[66],"For":[67],"each":[68],"modality":[70],"assume":[72],"an":[73],"individual":[74,163],"base":[75,164],"classifier":[76],"that":[77,138],"outputs":[78],"categorical":[80],"probability":[81],"distribution":[82],"fuse":[84],"these":[85],"distributions":[86],"using":[87],"Bayesian":[89,103],"fusion":[90],"method":[91,140],"Independent":[92],"Opinion":[93],"Pool.":[94],"While":[95],"existing":[96],"approaches":[97],"rely":[98],"on":[99,126],"heuristic":[100],"fusion,":[101],"our":[102,139,152],"is":[105,155],"theoretically":[106],"founded":[107],"fully":[109],"exploits":[110],"uncertainty":[112],"represented":[113],"distributions.":[116],"Experimental":[117],"evaluations":[118],"simulated":[121],"grid":[122],"world":[123],"scenario":[124],"real-world":[128],"human-robot":[129],"task":[131],"with":[132],"7-DoF":[134],"robot":[135],"arm":[136],"show":[137],"clearly":[141],"outperforms":[142],"closest":[144],"related":[145],"for":[147],"IRL.":[149],"robust":[157],"against":[158],"misclassifications":[159],"modalities\u2019":[162],"classifiers.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
