{"id":"https://openalex.org/W3131533760","doi":"https://doi.org/10.1109/iros45743.2020.9341124","title":"Adaptability Preserving Domain Decomposition for Stabilizing Sim2Real Reinforcement Learning","display_name":"Adaptability Preserving Domain Decomposition for Stabilizing Sim2Real Reinforcement Learning","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3131533760","doi":"https://doi.org/10.1109/iros45743.2020.9341124","mag":"3131533760"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9341124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5013839754","display_name":"Haichuan Gao","orcid":"https://orcid.org/0000-0002-5161-5326"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haichuan Gao","raw_affiliation_strings":["Tsinghua University,Beijing,China","Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107229776","display_name":"Zhile Yang","orcid":"https://orcid.org/0000-0002-7908-9524"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhile Yang","raw_affiliation_strings":["Tsinghua University,Beijing,China","Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008059019","display_name":"Xin Su","orcid":"https://orcid.org/0000-0003-0957-4628"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Su","raw_affiliation_strings":["Tsinghua University,Beijing,China","Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101667380","display_name":"Tian Tan","orcid":"https://orcid.org/0000-0001-9173-2984"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian Tan","raw_affiliation_strings":["Stanford University,Stanford,USA","Stanford University, Stanford, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Stanford,USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100352678","display_name":"Feng Chen","orcid":"https://orcid.org/0000-0001-9199-559X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Chen","raw_affiliation_strings":["Tsinghua University,Beijing,China","Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4403","last_page":"4410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.993399977684021,"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"}},{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.986299991607666,"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/adaptability","display_name":"Adaptability","score":0.9343223571777344},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8250716924667358},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.6198679804801941},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5937235951423645},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4818357229232788},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.4389571249485016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4014066159725189},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13772043585777283},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07204630970954895},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.05344322323799133}],"concepts":[{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.9343223571777344},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8250716924667358},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.6198679804801941},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5937235951423645},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4818357229232788},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.4389571249485016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4014066159725189},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13772043585777283},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07204630970954895},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.05344322323799133},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros45743.2020.9341124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W1576452626","https://openalex.org/W2291973609","https://openalex.org/W2521863123","https://openalex.org/W2530944449","https://openalex.org/W2534269850","https://openalex.org/W2605102758","https://openalex.org/W2736601468","https://openalex.org/W2737215781","https://openalex.org/W2767050701","https://openalex.org/W2949408529","https://openalex.org/W2952629144","https://openalex.org/W2962957005","https://openalex.org/W2963184124","https://openalex.org/W2963184939","https://openalex.org/W2963276406","https://openalex.org/W2963390419","https://openalex.org/W2963504951","https://openalex.org/W2963649664","https://openalex.org/W2964043796","https://openalex.org/W2964198579","https://openalex.org/W2964214518","https://openalex.org/W2967681060","https://openalex.org/W2969329576","https://openalex.org/W2972040422","https://openalex.org/W2982187448","https://openalex.org/W2990747716","https://openalex.org/W3003669699","https://openalex.org/W3004116079","https://openalex.org/W3030141984","https://openalex.org/W3101442004","https://openalex.org/W4288112468","https://openalex.org/W4288374418","https://openalex.org/W4297686387","https://openalex.org/W4297818513","https://openalex.org/W6616173779","https://openalex.org/W6692846177","https://openalex.org/W6696783566","https://openalex.org/W6726908607","https://openalex.org/W6728367041","https://openalex.org/W6728925229","https://openalex.org/W6740023956","https://openalex.org/W6741002519","https://openalex.org/W6741036684","https://openalex.org/W6752818329","https://openalex.org/W6761443123","https://openalex.org/W6763848572","https://openalex.org/W6767431140","https://openalex.org/W6769357845"],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W4389474468","https://openalex.org/W4300172004","https://openalex.org/W4321649381","https://openalex.org/W2997645659","https://openalex.org/W3180787869","https://openalex.org/W3203792196","https://openalex.org/W2955455867","https://openalex.org/W4295929828","https://openalex.org/W3156096827"],"abstract_inverted_index":{"In":[0],"sim-to-real":[1],"transfer":[2],"of":[3,82,93],"Reinforcement":[4],"Learning":[5],"(RL)":[6],"policies":[7],"for":[8,19,74],"robot":[9],"tasks,":[10],"Domain":[11,57],"Randomization":[12],"(DR)":[13],"is":[14,26,132],"a":[15,27,53,70,118],"widely":[16],"used":[17],"technique":[18],"improving":[20],"adaptability.":[21,114],"However,":[22],"in":[23,40,45,109],"DR":[24,36],"there":[25],"conflict":[28],"between":[29],"adaptability":[30,92],"and":[31,34,68,86],"training":[32,81,110],"stability,":[33],"heavy":[35],"tends":[37],"to":[38,66],"result":[39],"instability":[41],"or":[42],"even":[43],"failure":[44],"training.":[46],"To":[47],"relieve":[48],"this":[49],"conflict,":[50],"we":[51,88,116],"propose":[52],"new":[54],"algorithm":[55],"named":[56],"Decomposition":[58],"(DD)":[59],"that":[60,104],"decomposes":[61],"the":[62,80,91,94],"randomized":[63],"domain":[64],"according":[65],"environments":[67],"trains":[69],"separate":[71],"RL":[72,84],"policy":[73,96],"each":[75,83],"part.":[76],"This":[77],"decomposition":[78],"stabilizes":[79],"policy,":[85],"as":[87,134],"prove":[89],"theoretically,":[90],"overall":[95],"can":[97],"be":[98],"preserved.":[99],"Our":[100],"simulation":[101],"results":[102],"verify":[103],"DD":[105],"really":[106],"improves":[107],"stability":[108],"while":[111],"preserving":[112],"ideal":[113],"Further,":[115],"complete":[117],"complex":[119],"real-world":[120],"vision-based":[121],"patrolling":[122],"task":[123],"using":[124],"DD,":[125],"which":[126],"demonstrates":[127],"DD\u2019s":[128],"practicality.":[129],"A":[130],"video":[131],"attached":[133],"supplementary":[135],"material.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}