{"id":"https://openalex.org/W3003777383","doi":"https://doi.org/10.1109/iros40897.2019.8967966","title":"Fast and Safe Policy Adaptation via Alignment-based Transfer","display_name":"Fast and Safe Policy Adaptation via Alignment-based Transfer","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3003777383","doi":"https://doi.org/10.1109/iros40897.2019.8967966","mag":"3003777383"},"language":"en","primary_location":{"id":"doi:10.1109/iros40897.2019.8967966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5072360628","display_name":"Ji-Gang Kim","orcid":"https://orcid.org/0000-0003-3381-5241"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I158743462","display_name":"Seoul National University of Education","ror":"https://ror.org/01xts9v65","country_code":"KR","type":"education","lineage":["https://openalex.org/I158743462"]},{"id":"https://openalex.org/I2802457231","display_name":"New Generation University College","ror":"https://ror.org/015aem925","country_code":"ET","type":"education","lineage":["https://openalex.org/I2802457231"]}],"countries":["ET","KR"],"is_corresponding":false,"raw_author_name":"Jigang Kim","raw_affiliation_strings":["Seoul National University,Department of Mechanical and Aerospace Engineering,Seoul,Korea","Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Mechanical and Aerospace Engineering,Seoul,Korea","institution_ids":["https://openalex.org/I139264467","https://openalex.org/I2802457231","https://openalex.org/I158743462"]},{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102761136","display_name":"Seungwon Choi","orcid":"https://orcid.org/0000-0003-2327-3274"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I158743462","display_name":"Seoul National University of Education","ror":"https://ror.org/01xts9v65","country_code":"KR","type":"education","lineage":["https://openalex.org/I158743462"]},{"id":"https://openalex.org/I2802457231","display_name":"New Generation University College","ror":"https://ror.org/015aem925","country_code":"ET","type":"education","lineage":["https://openalex.org/I2802457231"]}],"countries":["ET","KR"],"is_corresponding":false,"raw_author_name":"Seungwon Choi","raw_affiliation_strings":["Seoul National University,Department of Mechanical and Aerospace Engineering,Seoul,Korea","Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Mechanical and Aerospace Engineering,Seoul,Korea","institution_ids":["https://openalex.org/I139264467","https://openalex.org/I2802457231","https://openalex.org/I158743462"]},{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073996122","display_name":"H. Jin Kim","orcid":"https://orcid.org/0000-0002-6819-1136"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I158743462","display_name":"Seoul National University of Education","ror":"https://ror.org/01xts9v65","country_code":"KR","type":"education","lineage":["https://openalex.org/I158743462"]},{"id":"https://openalex.org/I2802457231","display_name":"New Generation University College","ror":"https://ror.org/015aem925","country_code":"ET","type":"education","lineage":["https://openalex.org/I2802457231"]}],"countries":["ET","KR"],"is_corresponding":false,"raw_author_name":"H. Jin Kim","raw_affiliation_strings":["Seoul National University,Department of Mechanical and Aerospace Engineering,Seoul,Korea","Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Mechanical and Aerospace Engineering,Seoul,Korea","institution_ids":["https://openalex.org/I139264467","https://openalex.org/I2802457231","https://openalex.org/I158743462"]},{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1446,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61298671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"990","last_page":"996"},"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":0.9918000102043152,"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9876999855041504,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8349446058273315},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7822277545928955},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7409211993217468},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.7248953580856323},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6000720858573914},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5785560607910156},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.57212895154953},{"id":"https://openalex.org/keywords/policy-transfer","display_name":"Policy transfer","score":0.5568910241127014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.502140998840332},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.46566271781921387},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4538607895374298},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3829517066478729},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1101326048374176},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.09143584966659546}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8349446058273315},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7822277545928955},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7409211993217468},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.7248953580856323},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6000720858573914},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5785560607910156},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.57212895154953},{"id":"https://openalex.org/C2776731479","wikidata":"https://www.wikidata.org/wiki/Q15142682","display_name":"Policy transfer","level":2,"score":0.5568910241127014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.502140998840332},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.46566271781921387},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4538607895374298},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3829517066478729},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1101326048374176},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.09143584966659546},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C3116431","wikidata":"https://www.wikidata.org/wiki/Q31728","display_name":"Public administration","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros40897.2019.8967966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:s-space.snu.ac.kr:10371/187059","is_oa":false,"landing_page_url":"https://hdl.handle.net/10371/187059","pdf_url":null,"source":{"id":"https://openalex.org/S4306401345","display_name":"Seoul National University Open Repository (Seoul National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139264467","host_organization_name":"Seoul National University","host_organization_lineage":["https://openalex.org/I139264467"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1518931405","https://openalex.org/W1540685400","https://openalex.org/W1771410628","https://openalex.org/W1845972764","https://openalex.org/W1848094219","https://openalex.org/W2081034428","https://openalex.org/W2091714857","https://openalex.org/W2121103318","https://openalex.org/W2140135625","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2161395589","https://openalex.org/W2342662072","https://openalex.org/W2575705757","https://openalex.org/W2601322194","https://openalex.org/W2604763608","https://openalex.org/W2618318883","https://openalex.org/W2889925733","https://openalex.org/W2962803570","https://openalex.org/W2963094133","https://openalex.org/W2963175324","https://openalex.org/W2963184621","https://openalex.org/W2963641140","https://openalex.org/W2963669336","https://openalex.org/W2963703448","https://openalex.org/W2964340170","https://openalex.org/W3023058184","https://openalex.org/W4293545785","https://openalex.org/W4294555834","https://openalex.org/W4294562617","https://openalex.org/W4298082496","https://openalex.org/W6627932998","https://openalex.org/W6632235069","https://openalex.org/W6638018090","https://openalex.org/W6638853687","https://openalex.org/W6639175102","https://openalex.org/W6678367057","https://openalex.org/W6680657880","https://openalex.org/W6681861716","https://openalex.org/W6704571135","https://openalex.org/W6735944222","https://openalex.org/W6736057607","https://openalex.org/W6737893269","https://openalex.org/W6738483526","https://openalex.org/W6751535212"],"related_works":["https://openalex.org/W3095475970","https://openalex.org/W3017796982","https://openalex.org/W2027342354","https://openalex.org/W2906330542","https://openalex.org/W4390665401","https://openalex.org/W2142370952","https://openalex.org/W1512137381","https://openalex.org/W4393003728","https://openalex.org/W2035231162","https://openalex.org/W2998101326"],"abstract_inverted_index":{"Applying":[0],"deep":[1],"reinforcement":[2,37,161],"learning":[3,10,38,61,70,91,106],"to":[4,9,62,92,109,126,136],"physical":[5],"systems,":[6],"as":[7],"opposed":[8],"in":[11,16],"simulation,":[12],"presents":[13],"additional":[14],"challenges":[15],"terms":[17],"of":[18,26,36,52,69],"sample":[19],"efficiency":[20],"and":[21,32,116,128,139,155],"safety.":[22,144],"Collecting":[23],"large":[24],"amounts":[25],"hardware":[27],"demonstration":[28],"data":[29],"is":[30,87,107,134,153],"time-consuming":[31],"the":[33,42,49,113,131,149],"exploratory":[34],"behavior":[35],"algorithms":[39],"may":[40],"lead":[41],"system":[43],"into":[44],"dangerous":[45],"states,":[46],"especially":[47],"during":[48],"early":[50],"stages":[51],"training.":[53],"To":[54],"address":[55],"these":[56],"challenges,":[57],"we":[58,76],"apply":[59,123],"transfer":[60,90,105,141],"reuse":[63],"a":[64,78,82,94],"previously":[65],"learned":[66],"policy":[67,85,96,102,115,152],"instead":[68],"from":[71],"scratch.":[72],"In":[73],"this":[74,124],"paper,":[75],"propose":[77],"method":[79,125,133],"where":[80],"given":[81],"source":[83,114],"policy,":[84],"adaptation":[86],"performed":[88],"via":[89],"produce":[93],"target":[95,120,151],"suitable":[97],"for":[98],"real-world":[99],"deployment.":[100],"For":[101],"adaptation,":[103],"alignment-based":[104],"applied":[108],"trajectories":[110],"generated":[111],"by":[112],"their":[117],"corresponding":[118],"safe":[119],"trajectories.":[121],"We":[122,145],"manipulators":[127],"show":[129,147],"that":[130,148],"proposed":[132],"applicable":[135],"both":[137],"inter-task":[138],"inter-robot":[140],"whilst":[142],"considering":[143],"also":[146],"resulting":[150],"robust":[154],"can":[156],"be":[157],"further":[158],"improved":[159],"with":[160],"learning.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}