{"id":"https://openalex.org/W3216933777","doi":"https://doi.org/10.1109/icra46639.2022.9811770","title":"Robot Skill Adaptation via Soft Actor-Critic Gaussian Mixture Models","display_name":"Robot Skill Adaptation via Soft Actor-Critic Gaussian Mixture Models","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W3216933777","doi":"https://doi.org/10.1109/icra46639.2022.9811770","mag":"3216933777"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9811770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811770","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5016051882","display_name":"Iman Nematollahi","orcid":null},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Iman Nematollahi","raw_affiliation_strings":["University of Freiburg,Germany","University of Freiburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Freiburg,Germany","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"University of Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004569538","display_name":"Erick Rosete-Beas","orcid":null},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Erick Rosete-Beas","raw_affiliation_strings":["University of Freiburg,Germany","University of Freiburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Freiburg,Germany","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"University of Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097711479","display_name":"Adrian Rpfer","orcid":null},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Adrian Rpfer","raw_affiliation_strings":["University of Freiburg,Germany","University of Freiburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Freiburg,Germany","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"University of Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084779517","display_name":"Tim Welschehold","orcid":"https://orcid.org/0000-0003-1163-4992"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim Welschehold","raw_affiliation_strings":["University of Freiburg,Germany","University of Freiburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Freiburg,Germany","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"University of Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039639553","display_name":"Abhinav Valada","orcid":"https://orcid.org/0000-0003-4710-3114"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Abhinav Valada","raw_affiliation_strings":["University of Freiburg,Germany","University of Freiburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Freiburg,Germany","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"University of Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084499878","display_name":"Wolfram Burgard","orcid":"https://orcid.org/0000-0002-5680-6500"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfram Burgard","raw_affiliation_strings":["University of Freiburg,Germany","University of Freiburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Freiburg,Germany","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"University of Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161046081"],"apc_list":null,"apc_paid":null,"fwci":5.7518,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.97509524,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8651","last_page":"8657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9972000122070312,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","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/computer-science","display_name":"Computer science","score":0.7378230094909668},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6915076971054077},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.673143208026886},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6274702548980713},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5566992163658142},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5395829081535339},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5331695675849915},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49185943603515625},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4856201708316803},{"id":"https://openalex.org/keywords/programming-by-demonstration","display_name":"Programming by demonstration","score":0.46488282084465027},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4289637506008148},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37465375661849976}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7378230094909668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6915076971054077},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.673143208026886},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6274702548980713},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5566992163658142},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5395829081535339},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5331695675849915},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49185943603515625},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4856201708316803},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.46488282084465027},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4289637506008148},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37465375661849976},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra46639.2022.9811770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811770","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:freidok.uni-freiburg.de:238414","is_oa":false,"landing_page_url":"https://freidok.uni-freiburg.de/data/238414","pdf_url":null,"source":{"id":"https://openalex.org/S4306401057","display_name":"FreiDok plus (Universit\u00e4tsbibliothek Freiburg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I161046081","host_organization_name":"University of Freiburg","host_organization_lineage":["https://openalex.org/I161046081"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2022 IEEE International Conference on Robotics and Automation (ICRA). , 2022. - 8651-8657, ISBN: 978-1-72819-681-7","raw_type":"article_in_conference_proceedings"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W1684361744","https://openalex.org/W2049633694","https://openalex.org/W2072863821","https://openalex.org/W2125602005","https://openalex.org/W2129202194","https://openalex.org/W2135043890","https://openalex.org/W2136719407","https://openalex.org/W2154543878","https://openalex.org/W2161395589","https://openalex.org/W2218318129","https://openalex.org/W2609992816","https://openalex.org/W2736601468","https://openalex.org/W2755546070","https://openalex.org/W2769112066","https://openalex.org/W2781726626","https://openalex.org/W2784005481","https://openalex.org/W2787938642","https://openalex.org/W2899184737","https://openalex.org/W2910448276","https://openalex.org/W2938421504","https://openalex.org/W2962730651","https://openalex.org/W2962732055","https://openalex.org/W2962746398","https://openalex.org/W2963092423","https://openalex.org/W2963262330","https://openalex.org/W2963277051","https://openalex.org/W2963305465","https://openalex.org/W2963402657","https://openalex.org/W2963923407","https://openalex.org/W2967399099","https://openalex.org/W2967936796","https://openalex.org/W2986303149","https://openalex.org/W3006398608","https://openalex.org/W3006904299","https://openalex.org/W3008303301","https://openalex.org/W3012366945","https://openalex.org/W3015225138","https://openalex.org/W3029926839","https://openalex.org/W3036642894","https://openalex.org/W3090600213","https://openalex.org/W3090971691","https://openalex.org/W3094336301","https://openalex.org/W3100818121","https://openalex.org/W3104485462","https://openalex.org/W3106892592","https://openalex.org/W3111013878","https://openalex.org/W3112669067","https://openalex.org/W3130717831","https://openalex.org/W3131005319","https://openalex.org/W3132689247","https://openalex.org/W3164834180","https://openalex.org/W3166834117","https://openalex.org/W3209555046","https://openalex.org/W4211008118","https://openalex.org/W6688386640","https://openalex.org/W6712884540","https://openalex.org/W6718092244","https://openalex.org/W6741002519","https://openalex.org/W6744181227","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6755802134","https://openalex.org/W6764800732","https://openalex.org/W6778324997","https://openalex.org/W6784781581","https://openalex.org/W6785733472","https://openalex.org/W6786993690"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W4323768008","https://openalex.org/W2586732548","https://openalex.org/W2143599199","https://openalex.org/W2047222776","https://openalex.org/W4387678044"],"abstract_inverted_index":{"$A$core":[0],"challenge":[1],"for":[2],"an":[3],"autonomous":[4],"agent":[5],"acting":[6],"in":[7,45,91,151,163],"the":[8,66,88,100,113,133,158],"real":[9],"world":[10],"is":[11],"to":[12,18,31,38,139,145],"adapt":[13],"its":[14,21],"repertoire":[15],"of":[16,29,108,135,160],"skills":[17,30,44,81,90,138,166],"cope":[19],"with":[20,99,112],"noisy":[22],"perception":[23],"and":[24,40,86,118,154,174,181],"dynamics.":[25],"To":[26,61],"scale":[27],"learning":[28,109,116],"long-horizon":[32],"tasks,":[33],"robots":[34],"should":[35],"be":[36],"able":[37],"learn":[39],"later":[41],"refine":[42],"their":[43,92,120],"a":[46,74,83],"structured":[47],"manner":[48],"through":[49,82,97],"trajectories":[50],"rather":[51],"than":[52],"making":[53],"instantaneous":[54],"decisions":[55],"individually":[56],"at":[57,186],"each":[58],"time":[59],"step.":[60],"this":[62],"end,":[63],"we":[64],"propose":[65],"Soft":[67],"Actor-":[68],"Critic":[69],"Gaussian":[70],"Mixture":[71],"Model":[72],"(SAC-GMM),":[73],"novel":[75],"hybrid":[76],"approach":[77,103],"that":[78,125,143],"learns":[79],"robot":[80,165],"dynamical":[84],"system":[85],"adapts":[87],"learned":[89,137],"own":[93],"trajectory":[94],"distribution":[95],"space":[96],"interactions":[98],"environment.":[101],"Our":[102],"combines":[104],"classical":[105],"robotics":[106],"techniques":[107],"from":[110],"demonstration":[111],"deep":[114],"reinforcement":[115],"framework":[117],"exploits":[119],"complementary":[121],"nature.":[122],"We":[123],"show":[124],"our":[126,161],"method":[127,162],"utilizes":[128],"sensors":[129],"solely":[130],"available":[131,185],"during":[132],"execution":[134],"preliminarily":[136],"extract":[140],"relevant":[141],"features":[142],"lead":[144],"faster":[146],"skill":[147],"refinement.":[148],"Extensive":[149],"evaluations":[150],"both":[152],"simulation":[153],"real-world":[155],"environments":[156],"demonstrate":[157],"effectiveness":[159],"refining":[164],"by":[167],"leveraging":[168],"physical":[169],"interactions,":[170],"high-dimensional":[171],"sensory":[172],"data,":[173],"sparse":[175],"task":[176],"completion":[177],"rewards.":[178],"Videos,":[179],"code,":[180],"pre-trained":[182],"models":[183],"are":[184],"http://sac-gmm.cs.uni-freiburg.de.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}