{"id":"https://openalex.org/W4312900875","doi":"https://doi.org/10.1109/case49997.2022.9926540","title":"Expert Initialized Reinforcement Learning with Application to Robotic Assembly","display_name":"Expert Initialized Reinforcement Learning with Application to Robotic Assembly","publication_year":2022,"publication_date":"2022-08-20","ids":{"openalex":"https://openalex.org/W4312900875","doi":"https://doi.org/10.1109/case49997.2022.9926540"},"language":"en","primary_location":{"id":"doi:10.1109/case49997.2022.9926540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case49997.2022.9926540","pdf_url":null,"source":{"id":"https://openalex.org/S4363607892","display_name":"2022 IEEE 18th International Conference on Automation Science and Engineering (CASE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 18th International Conference on Automation Science and Engineering (CASE)","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/A5012865633","display_name":"Jeppe Langaa","orcid":"https://orcid.org/0000-0002-2527-154X"},"institutions":[{"id":"https://openalex.org/I184886455","display_name":"Maersk (Denmark)","ror":"https://ror.org/046gbzb64","country_code":"DK","type":"company","lineage":["https://openalex.org/I184886455"]},{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Jeppe Langaa","raw_affiliation_strings":["University of Southern Denmark,Maersk McKinney Moller Institute,Odense,Denmark","Maersk McKinney Moller Institute, University of Southern Denmark, Odense, Denmark"],"affiliations":[{"raw_affiliation_string":"University of Southern Denmark,Maersk McKinney Moller Institute,Odense,Denmark","institution_ids":["https://openalex.org/I184886455","https://openalex.org/I177969490"]},{"raw_affiliation_string":"Maersk McKinney Moller Institute, University of Southern Denmark, Odense, Denmark","institution_ids":["https://openalex.org/I184886455","https://openalex.org/I177969490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088328087","display_name":"Christoffer Sloth","orcid":"https://orcid.org/0000-0002-3309-6278"},"institutions":[{"id":"https://openalex.org/I184886455","display_name":"Maersk (Denmark)","ror":"https://ror.org/046gbzb64","country_code":"DK","type":"company","lineage":["https://openalex.org/I184886455"]},{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Christoffer Sloth","raw_affiliation_strings":["University of Southern Denmark,Maersk McKinney Moller Institute,Odense,Denmark","Maersk McKinney Moller Institute, University of Southern Denmark, Odense, Denmark"],"affiliations":[{"raw_affiliation_string":"University of Southern Denmark,Maersk McKinney Moller Institute,Odense,Denmark","institution_ids":["https://openalex.org/I184886455","https://openalex.org/I177969490"]},{"raw_affiliation_string":"Maersk McKinney Moller Institute, University of Southern Denmark, Odense, Denmark","institution_ids":["https://openalex.org/I184886455","https://openalex.org/I177969490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012865633"],"corresponding_institution_ids":["https://openalex.org/I177969490","https://openalex.org/I184886455"],"apc_list":null,"apc_paid":null,"fwci":0.5235,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.64986484,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1405","last_page":"1410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9873999953269958,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9534000158309937,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8804550170898438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6659536361694336},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5967437028884888},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5844240188598633},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5787983536720276},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.545027494430542},{"id":"https://openalex.org/keywords/admittance","display_name":"Admittance","score":0.5305125117301941},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5150210857391357},{"id":"https://openalex.org/keywords/industrial-robot","display_name":"Industrial robot","score":0.4191582202911377},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.4085696339607239},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21644729375839233}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8804550170898438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6659536361694336},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5967437028884888},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5844240188598633},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5787983536720276},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.545027494430542},{"id":"https://openalex.org/C108811297","wikidata":"https://www.wikidata.org/wiki/Q214518","display_name":"Admittance","level":3,"score":0.5305125117301941},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5150210857391357},{"id":"https://openalex.org/C2776126113","wikidata":"https://www.wikidata.org/wiki/Q1128980","display_name":"Industrial robot","level":3,"score":0.4191582202911377},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4085696339607239},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21644729375839233},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C17829176","wikidata":"https://www.wikidata.org/wiki/Q179043","display_name":"Electrical impedance","level":2,"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/case49997.2022.9926540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case49997.2022.9926540","pdf_url":null,"source":{"id":"https://openalex.org/S4363607892","display_name":"2022 IEEE 18th International Conference on Automation Science and Engineering (CASE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 18th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"},{"id":"pmh:oai:sdu.dk:openaire_cris_publications/0f75afbb-d799-445f-8615-d3189dfe7f18","is_oa":false,"landing_page_url":"https://portal.findresearcher.sdu.dk/da/publications/0f75afbb-d799-445f-8615-d3189dfe7f18","pdf_url":null,"source":{"id":"https://openalex.org/S4306400424","display_name":"University of Southern Denmark Research Portal (University of Southern Denmark)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177969490","host_organization_name":"University of Southern Denmark","host_organization_lineage":["https://openalex.org/I177969490"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Langaa, J & Sloth, C 2022, Expert Initialized Reinforcement Learning with Application to Robotic Assembly. in 2022 IEEE 18th International Conference on Automation Science and Engineering (CASE). IEEE Computer Society, Proceedings - IEEE International Conference on Automation Science and Engineering, vol. 2022-August, pp. 1405-1410, 18th IEEE International Conference on Automation Science and Engineering, CASE 2022, Mexico City, Mexico, 20/08/2022. https://doi.org/10.1109/CASE49997.2022.9926540","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334111","display_name":"Innovation Fund","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1959608418","https://openalex.org/W1980516134","https://openalex.org/W2017957151","https://openalex.org/W2068088498","https://openalex.org/W2566523535","https://openalex.org/W2781935341","https://openalex.org/W2787938642","https://openalex.org/W2793264449","https://openalex.org/W2885163910","https://openalex.org/W2890208753","https://openalex.org/W2914304175","https://openalex.org/W2963940579","https://openalex.org/W2973229164","https://openalex.org/W2981030070","https://openalex.org/W2989847975","https://openalex.org/W2990747716","https://openalex.org/W3037625705","https://openalex.org/W3118210634","https://openalex.org/W6640963894","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6748839928","https://openalex.org/W6754184789","https://openalex.org/W6768977950"],"related_works":["https://openalex.org/W2982321410","https://openalex.org/W2392004567","https://openalex.org/W2200472972","https://openalex.org/W2940029036","https://openalex.org/W4388292429","https://openalex.org/W2756595502","https://openalex.org/W2031643172","https://openalex.org/W3205034227","https://openalex.org/W1594265855","https://openalex.org/W2740013582"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,51,61,111,117,140],"advantages":[4],"and":[5,18,27,53,82],"boundaries":[6],"of":[7,21,55,80,98],"actor-critic":[8,62],"reinforcement":[9,63],"learning":[10,64],"algorithms":[11],"in":[12,38,94,136],"an":[13,70,75,133],"industrial":[14,76],"setting.":[15],"We":[16],"compare":[17],"discuss":[19],"Cycle":[20,79,97],"Learning,":[22],"Deep":[23,30,85],"Deterministic":[24,31,86],"Policy":[25,32,87],"Gradient":[26,33,88],"Twin":[28,83],"Delayed":[29,84],"with":[34,60,69],"respect":[35],"to":[36,73,90,101,110,119,131,138,143],"performance":[37],"simulation":[39],"as":[40,42],"well":[41],"on":[43,104],"a":[44,105,129,144],"real":[45,106,145],"robot":[46],"setup.":[47],"Furthermore,":[48],"it":[49,68,127],"emphasizes":[50],"importance":[52],"potential":[54],"combining":[56],"demonstrated":[57,125],"expert":[58],"behavior":[59,112,142],"setting":[65],"while":[66,96],"using":[67],"admittance":[71,134],"controller":[72,135],"solve":[74],"assembly":[77],"task.":[78],"Learning":[81,99],"showed":[89],"be":[91,102],"equally":[92],"usable":[93],"simulation,":[95],"proved":[100],"best":[103],"world":[107],"application":[108],"due":[109],"cloning":[113],"loss":[114],"that":[115,126],"enables":[116],"agent":[118],"learn":[120],"rapidly.":[121],"The":[122],"results":[123],"also":[124],"is":[128],"necessity":[130],"incorporate":[132],"order":[137],"transfer":[139],"learned":[141],"robot.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}