{"id":"https://openalex.org/W2737821837","doi":"https://doi.org/10.1109/icra.2017.7989686","title":"Adapting learned robotics behaviours through policy adjustment","display_name":"Adapting learned robotics behaviours through policy adjustment","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2737821837","doi":"https://doi.org/10.1109/icra.2017.7989686","mag":"2737821837"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2017.7989686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","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/A5007491151","display_name":"Juan Camilo Gamboa Higuera","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Juan Camilo Gamboa Higuera","raw_affiliation_strings":["McGill University, Montreal, QC, CA"],"affiliations":[{"raw_affiliation_string":"McGill University, Montreal, QC, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109496264","display_name":"David Meger","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"David Meger","raw_affiliation_strings":["Center for Intelligent Machines and the School of Computer Science, McGill University, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Center for Intelligent Machines and the School of Computer Science, McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075441381","display_name":"Gregory Dudek","orcid":"https://orcid.org/0000-0001-5040-4925"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gregory Dudek","raw_affiliation_strings":["Center for Intelligent Machines and the School of Computer Science, McGill University, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"Center for Intelligent Machines and the School of Computer Science, McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007491151"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5352,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91810395,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5837","last_page":"5843"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9894000291824341,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9575999975204468,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.738950252532959},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6566722393035889},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.6533267498016357},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5916978716850281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5851036906242371},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5627561807632446},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5488831996917725},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4972400963306427},{"id":"https://openalex.org/keywords/physical-system","display_name":"Physical system","score":0.45902830362319946},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.42344963550567627},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.364967405796051},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.31686410307884216},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14309415221214294},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1112903356552124}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.738950252532959},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6566722393035889},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.6533267498016357},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5916978716850281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5851036906242371},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5627561807632446},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5488831996917725},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4972400963306427},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.45902830362319946},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.42344963550567627},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.364967405796051},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.31686410307884216},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14309415221214294},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1112903356552124},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2017.7989686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1511334422","https://openalex.org/W1587009522","https://openalex.org/W1897171481","https://openalex.org/W1965675101","https://openalex.org/W1977655452","https://openalex.org/W2018705428","https://openalex.org/W2042520683","https://openalex.org/W2097381042","https://openalex.org/W2104733512","https://openalex.org/W2158796564","https://openalex.org/W2170912685","https://openalex.org/W2951060109","https://openalex.org/W4211089519","https://openalex.org/W6639724578","https://openalex.org/W6655145722","https://openalex.org/W6674600207","https://openalex.org/W6675999342","https://openalex.org/W6682968728"],"related_works":["https://openalex.org/W962423920","https://openalex.org/W2387968248","https://openalex.org/W2120821724","https://openalex.org/W2350715914","https://openalex.org/W2379529020","https://openalex.org/W2101175215","https://openalex.org/W2893549521","https://openalex.org/W1562157883","https://openalex.org/W2330311678","https://openalex.org/W2388509240"],"abstract_inverted_index":{"We":[0,113,130],"present":[1],"an":[2,37],"approach":[3,65,116,134],"to":[4,55,88,100,148],"learning":[5],"control":[6],"policies":[7,18],"for":[8],"physical":[9,34,137],"robots":[10],"that":[11,19,67],"achieves":[12],"high":[13],"efficiency":[14],"by":[15,71],"adjusting":[16],"existing":[17],"have":[20],"been":[21],"learned":[22,50,144],"on":[23,51,77],"similar":[24,30,61],"source":[25,53,73,94],"systems,":[26],"such":[27],"as":[28,46],"a":[29,48,52,57,90,109,125,136,143],"robot":[31,74,95,103],"with":[32,135],"different":[33],"parameters,":[35],"or":[36],"approximate":[38],"dynamics":[39],"model":[40],"simulator.":[41],"This":[42],"can":[43],"be":[44],"viewed":[45],"calibrating":[47],"policy":[49,110,145],"system,":[54,139],"match":[56],"desired":[58],"behaviour":[59],"in":[60,117,119],"target":[62,79,102],"systems.":[63],"Our":[64],"assumes":[66],"the":[68,72,78,93,101,120,149,152],"trajectories":[69],"described":[70],"are":[75],"feasible":[76],"robot.":[80],"By":[81],"making":[82],"this":[83],"assumption,":[84],"we":[85,107,141],"only":[86],"need":[87],"learn":[89],"mapping":[91],"from":[92],"state":[96],"and":[97,124],"action":[98,104],"spaces":[99],"space,":[105],"which":[106],"call":[108],"adjustment":[111],"model.":[112],"demonstrate":[114],"our":[115,133],"simulation":[118],"cart-pole":[121,138],"balancing":[122],"task":[123],"two":[126],"link":[127],"double":[128],"pendulum.":[129],"also":[131],"validate":[132],"where":[140],"adjust":[142],"under":[146],"changes":[147],"weight":[150],"of":[151],"pole.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}