{"id":"https://openalex.org/W6906126677","doi":"https://doi.org/10.15496/publikation-71149","title":"Learning robust control policies for real robots","display_name":"Learning robust control policies for real robots","publication_year":2022,"publication_date":"2022-07-27","ids":{"openalex":"https://openalex.org/W6906126677","doi":"https://doi.org/10.15496/publikation-71149"},"language":"en","primary_location":{"id":"doi:10.15496/publikation-71149","is_oa":true,"landing_page_url":"https://doi.org/10.15496/publikation-71149","pdf_url":null,"source":{"id":"https://openalex.org/S7407053000","display_name":"Universit\u00e4tsbibliothek T\u00fcbingen","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.15496/publikation-71149","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bogdanovic, Miroslav","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bogdanovic, Miroslav","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.605400025844574},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5587999820709229},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.555400013923645},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5062000155448914},{"id":"https://openalex.org/keywords/robust-control","display_name":"Robust control","score":0.4966000020503998},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4223000109195709},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.3855000138282776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6748999953269958},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.605400025844574},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5587999820709229},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.555400013923645},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5062000155448914},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.4966000020503998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48089998960494995},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3817000091075897},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3260999917984009},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3027999997138977},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2928999960422516},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.15496/publikation-71149","is_oa":true,"landing_page_url":"https://doi.org/10.15496/publikation-71149","pdf_url":null,"source":{"id":"https://openalex.org/S7407053000","display_name":"Universit\u00e4tsbibliothek T\u00fcbingen","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.15496/publikation-71149","is_oa":true,"landing_page_url":"https://doi.org/10.15496/publikation-71149","pdf_url":null,"source":{"id":"https://openalex.org/S7407053000","display_name":"Universit\u00e4tsbibliothek T\u00fcbingen","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,96,122,162],"this":[1,94],"thesis":[2],"we":[3,75,100,125,166],"deal":[4],"with":[5,45],"the":[6,48,78,97,123,163],"problem":[7],"of":[8,93],"using":[9],"deep":[10],"reinforcement":[11],"learning":[12,105,128],"to":[13,27,32,39,54,62,66,72,83,116,147,151,155,176],"generate":[14],"robust":[15,71,177],"policies":[16,56,68,131,150],"for":[17,104],"real":[18,63,79,156,186],"robots.":[19],"We":[20,81],"identify":[21],"three":[22,88],"key":[23],"issues":[24,86],"that":[25,69,90,171,180],"need":[26],"be":[28,182],"tackled":[29],"in":[30,42,47,58,77,118],"order":[31],"make":[33],"progress":[34],"along":[35],"these":[36,85,149],"lines.":[37],"How":[38,53,65],"perform":[40],"exploration":[41,107],"robotic":[43],"tasks,":[44,140],"discontinuities":[46],"environment":[49,73],"and":[50,158],"sparse":[51],"rewards.":[52],"ensure":[55],"trained":[57],"simulation":[59],"transfer":[60,154],"well":[61,142],"systems.":[64,187],"build":[67],"are":[70,91],"variability":[74],"encounter":[76],"world.":[80],"aim":[82],"tackle":[84],"through":[87],"papers":[89],"part":[92],"thesis.":[95],"first":[98],"one,":[99],"present":[101],"an":[102,106],"approach":[103,170],"process":[108],"based":[109],"on":[110,137,185],"data":[111],"from":[112,173],"previously":[113],"solved":[114],"tasks":[115],"aid":[117],"solving":[119],"new":[120],"ones.":[121],"second,":[124],"show":[126],"how":[127],"variable":[129],"gain":[130],"can":[132,181],"produce":[133],"better":[134],"performing":[135],"solutions":[136],"contact":[138],"sensitive":[139],"as":[141,143],"propose":[144,167],"a":[145,168],"way":[146],"regularize":[148],"enable":[152],"direct":[153],"systems":[157],"improve":[159],"their":[160],"interpretability.":[161],"final":[164],"work,":[165],"two-stage":[169],"goes":[172],"simple":[174],"demonstrations":[175],"adaptive":[178],"behaviors":[179],"directly":[183],"deployed":[184]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}