{"id":"https://openalex.org/W4285066157","doi":"https://doi.org/10.1109/lra.2022.3184805","title":"MPR-RL: Multi-Prior Regularized Reinforcement Learning for Knowledge Transfer","display_name":"MPR-RL: Multi-Prior Regularized Reinforcement Learning for Knowledge Transfer","publication_year":2022,"publication_date":"2022-06-22","ids":{"openalex":"https://openalex.org/W4285066157","doi":"https://doi.org/10.1109/lra.2022.3184805"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2022.3184805","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2022.3184805","pdf_url":"https://ieeexplore.ieee.org/ielx7/7083369/9750005/09803274.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/7083369/9750005/09803274.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021059709","display_name":"Quantao Yang","orcid":"https://orcid.org/0000-0001-5655-0990"},"institutions":[{"id":"https://openalex.org/I26437253","display_name":"\u00d6rebro University","ror":"https://ror.org/05kytsw45","country_code":"SE","type":"education","lineage":["https://openalex.org/I26437253"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Quantao Yang","raw_affiliation_strings":["Autonomous Mobile Manipulation lab at the Center for Applied Autonomous Sensor Systems (AASS), Örebro University, Örebro, Sweden"],"raw_orcid":"https://orcid.org/0000-0001-5655-0990","affiliations":[{"raw_affiliation_string":"Autonomous Mobile Manipulation lab at the Center for Applied Autonomous Sensor Systems (AASS), Örebro University, Örebro, Sweden","institution_ids":["https://openalex.org/I26437253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023785357","display_name":"Johannes A. Stork","orcid":"https://orcid.org/0000-0003-3958-6179"},"institutions":[{"id":"https://openalex.org/I26437253","display_name":"\u00d6rebro University","ror":"https://ror.org/05kytsw45","country_code":"SE","type":"education","lineage":["https://openalex.org/I26437253"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Johannes A. Stork","raw_affiliation_strings":["Autonomous Mobile Manipulation lab at the Center for Applied Autonomous Sensor Systems (AASS), Örebro University, Örebro, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-3958-6179","affiliations":[{"raw_affiliation_string":"Autonomous Mobile Manipulation lab at the Center for Applied Autonomous Sensor Systems (AASS), Örebro University, Örebro, Sweden","institution_ids":["https://openalex.org/I26437253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044352907","display_name":"Todor Stoyanov","orcid":"https://orcid.org/0000-0002-6013-4874"},"institutions":[{"id":"https://openalex.org/I26437253","display_name":"\u00d6rebro University","ror":"https://ror.org/05kytsw45","country_code":"SE","type":"education","lineage":["https://openalex.org/I26437253"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Todor Stoyanov","raw_affiliation_strings":["Autonomous Mobile Manipulation lab at the Center for Applied Autonomous Sensor Systems (AASS), Örebro University, Örebro, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-6013-4874","affiliations":[{"raw_affiliation_string":"Autonomous Mobile Manipulation lab at the Center for Applied Autonomous Sensor Systems (AASS), Örebro University, Örebro, Sweden","institution_ids":["https://openalex.org/I26437253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021059709"],"corresponding_institution_ids":["https://openalex.org/I26437253"],"apc_list":null,"apc_paid":null,"fwci":1.0936,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.75934557,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"7","issue":"3","first_page":"7652","last_page":"7659"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9722999930381775,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8053923845291138},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7718502283096313},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7198227047920227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.644427478313446},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6388249397277832},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6056409478187561},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5946661829948425},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5717074871063232},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5570098161697388},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5104507207870483},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5082821249961853},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4655279517173767},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.1826835572719574},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08222934603691101},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.078835129737854}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8053923845291138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7718502283096313},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7198227047920227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.644427478313446},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6388249397277832},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6056409478187561},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5946661829948425},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5717074871063232},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5570098161697388},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5104507207870483},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5082821249961853},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4655279517173767},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.1826835572719574},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08222934603691101},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.078835129737854},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2022.3184805","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2022.3184805","pdf_url":"https://ieeexplore.ieee.org/ielx7/7083369/9750005/09803274.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/lra.2022.3184805","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2022.3184805","pdf_url":"https://ieeexplore.ieee.org/ielx7/7083369/9750005/09803274.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285066157.pdf","grobid_xml":"https://content.openalex.org/works/W4285066157.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2097381042","https://openalex.org/W2605102758","https://openalex.org/W2767050701","https://openalex.org/W2903630557","https://openalex.org/W2918049070","https://openalex.org/W2949600457","https://openalex.org/W2953431737","https://openalex.org/W2962899390","https://openalex.org/W2964214518","https://openalex.org/W2964262254","https://openalex.org/W2968021416","https://openalex.org/W3016525976","https://openalex.org/W3090612618","https://openalex.org/W3101442004","https://openalex.org/W3130984490","https://openalex.org/W3207591725","https://openalex.org/W4225873172","https://openalex.org/W6639732818","https://openalex.org/W6640963894","https://openalex.org/W6674600207","https://openalex.org/W6736057607","https://openalex.org/W6736469832","https://openalex.org/W6740023956","https://openalex.org/W6742103744","https://openalex.org/W6747473740","https://openalex.org/W6755365793","https://openalex.org/W6755890616","https://openalex.org/W6760698134","https://openalex.org/W6761443123","https://openalex.org/W6768560635","https://openalex.org/W6776601253","https://openalex.org/W6784712800","https://openalex.org/W6785876034","https://openalex.org/W6798895900","https://openalex.org/W7011045397"],"related_works":["https://openalex.org/W2821676139","https://openalex.org/W3043695725","https://openalex.org/W4382138864","https://openalex.org/W4387770285","https://openalex.org/W3022215768","https://openalex.org/W3135975972","https://openalex.org/W3016888008","https://openalex.org/W4385864216","https://openalex.org/W4387183713","https://openalex.org/W2165698076"],"abstract_inverted_index":{"In":[0,64],"manufacturing,":[1],"assembly":[2],"tasks":[3,79,162,169],"have":[4,147,171],"been":[5,173],"a":[6,22,38,49,52,75,113,131,152,157,187,195],"challenge":[7,70],"for":[8,112,142],"learning":[9,19,109],"algorithms":[10],"due":[11],"to":[12,25,36,51,87,96,107,167],"variant":[13],"dynamics":[14],"of":[15,47,71,77,104,159,197],"different":[16],"environments.":[17],"Reinforcement":[18],"(RL)":[20],"is":[21,32,44,183],"promising":[23],"framework":[24],"automatically":[26],"learn":[27,88],"these":[28],"tasks,":[29],"yet":[30],"it":[31],"still":[33],"not":[34,204],"easy":[35],"apply":[37],"learned":[39],"policy":[40,111],"or":[41],"skill,":[42],"that":[43,170],"the":[45,57,69,92,102,110,118,121,125,136],"ability":[46],"solving":[48],"task,":[50],"similar":[53,78],"environment":[54],"even":[55],"if":[56],"deployment":[58],"conditions":[59],"are":[60],"only":[61,194],"slightly":[62],"different.":[63],"this":[65],"letter,":[66],"we":[67],"address":[68],"transferring":[72],"knowledge":[73],"within":[74],"family":[76,103],"by":[80,116],"leveraging":[81],"multiple":[82],"skill":[83,94,105,137],"priors.":[84],"We":[85,146],"propose":[86],"prior":[89,126,144],"distribution":[90],"over":[91],"specific":[93],"required":[95],"accomplish":[97],"each":[98,143],"task":[99,115,123,153],"and":[100,124,156,163],"compose":[101],"priors":[106],"guide":[108],"new":[114,168],"comparing":[117],"similarity":[119],"between":[120],"target":[122],"ones.":[127],"Our":[128,177],"method":[129,150,182],"learns":[130],"latent":[132],"action":[133],"space":[134],"representing":[135],"embedding":[138],"from":[139,200],"demonstrated":[140,198],"trajectories":[141,199],"task.":[145],"evaluated":[148],"our":[149],"on":[151,186],"in":[154],"simulation":[155],"set":[158,196],"peg-in-hole":[160],"insertion":[161],"demonstrate":[164],"better":[165],"generalization":[166],"never":[172],"encountered":[174],"during":[175],"training.":[176],"Multi-Prior":[178],"Regularized":[179],"RL":[180],"(MPR-RL)":[181],"deployed":[184],"directly":[185],"real":[188],"world":[189],"Franka":[190],"Panda":[191],"arm,":[192],"requiring":[193],"similar,":[201],"but":[202],"crucially":[203],"identical,":[205],"problem":[206],"instances.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}