{"id":"https://openalex.org/W1517081929","doi":"https://doi.org/10.1109/icra.2015.7139552","title":"Reducing hardware experiments for model learning and policy optimization","display_name":"Reducing hardware experiments for model learning and policy optimization","publication_year":2015,"publication_date":"2015-05-01","ids":{"openalex":"https://openalex.org/W1517081929","doi":"https://doi.org/10.1109/icra.2015.7139552","mag":"1517081929"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2015.7139552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2015.7139552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/A5064581452","display_name":"Sehoon Ha","orcid":"https://orcid.org/0000-0002-1972-328X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sehoon Ha","raw_affiliation_strings":["Georgia Institute of Technology, Georgia Institute of Technology","Georgia Institute of Technology,  USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology,  USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062092630","display_name":"Katsu Yamane","orcid":"https://orcid.org/0000-0002-6056-9210"},"institutions":[{"id":"https://openalex.org/I4210142140","display_name":"Walt Disney (United States)","ror":"https://ror.org/04eg47h42","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142140"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katsu Yamane","raw_affiliation_strings":["Disney Research, Pittsburgh","Disney Research, Pittsburgh, USA"],"affiliations":[{"raw_affiliation_string":"Disney Research, Pittsburgh","institution_ids":["https://openalex.org/I4210142140"]},{"raw_affiliation_string":"Disney Research, Pittsburgh, USA","institution_ids":["https://openalex.org/I4210142140"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5064581452"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":4.7458,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.9504001,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2620","last_page":"2626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9919000267982483,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.7867516279220581},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.6280790567398071},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5527997612953186},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5017240047454834},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.4713461101055145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33747386932373047},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.32767924666404724}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7867516279220581},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.6280790567398071},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5527997612953186},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5017240047454834},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.4713461101055145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33747386932373047},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.32767924666404724},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2015.7139552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2015.7139552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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":33,"referenced_works":["https://openalex.org/W1491843047","https://openalex.org/W1540685400","https://openalex.org/W1969140852","https://openalex.org/W1977655452","https://openalex.org/W2021732065","https://openalex.org/W2029809384","https://openalex.org/W2041851440","https://openalex.org/W2042520683","https://openalex.org/W2048226872","https://openalex.org/W2083456681","https://openalex.org/W2113741278","https://openalex.org/W2120742447","https://openalex.org/W2132602063","https://openalex.org/W2140135625","https://openalex.org/W2151268438","https://openalex.org/W2155307968","https://openalex.org/W2158796564","https://openalex.org/W2162717641","https://openalex.org/W2166063021","https://openalex.org/W2167117957","https://openalex.org/W2167647761","https://openalex.org/W2185967851","https://openalex.org/W2610686804","https://openalex.org/W2964349150","https://openalex.org/W4236696173","https://openalex.org/W4245108548","https://openalex.org/W6632235069","https://openalex.org/W6653435097","https://openalex.org/W6680657880","https://openalex.org/W6682968728","https://openalex.org/W6683735925","https://openalex.org/W6684451488","https://openalex.org/W7066478640"],"related_works":["https://openalex.org/W2475116013","https://openalex.org/W2770018148","https://openalex.org/W2358308169","https://openalex.org/W2385135707","https://openalex.org/W2140315382","https://openalex.org/W2059109728","https://openalex.org/W322691623","https://openalex.org/W2494989134","https://openalex.org/W2509444723","https://openalex.org/W2004958254"],"abstract_inverted_index":{"Conducting":[0],"hardware":[1,34,55,116,124],"experiment":[2],"is":[3,29],"often":[4],"expensive":[5],"in":[6,31,35,45,49,59,156],"various":[7],"aspects":[8],"such":[9,36,65,101],"as":[10,66,102,122,126],"potential":[11],"damage":[12],"to":[13,22,57,163],"the":[14,17,24,60,69,131,138,149,153,174],"robot":[15,25,104],"and":[16,77,106,118,144],"number":[18,90],"of":[19,33,91,129,167],"people":[20],"required":[21],"operate":[23],"safely.":[26],"Computer":[27],"simulation":[28,43,50,142],"used":[30],"place":[32],"cases,":[37],"but":[38],"it":[39],"suffers":[40],"from":[41,133],"so-called":[42],"bias":[44],"which":[46,93],"policies":[47,120],"tuned":[48],"do":[51,72],"not":[52,73,95],"work":[53],"on":[54,68,152],"due":[56],"differences":[58],"two":[61],"systems.":[62],"Model-free":[63],"methods":[64,85],"Q-Learning,":[67],"other":[70],"hand,":[71],"require":[74,87],"a":[75,88,141],"model":[76,132,143,155,170],"therefore":[78],"can":[79],"avoid":[80],"this":[81],"issue.":[82],"However,":[83],"these":[84],"typically":[86],"large":[89],"experiments,":[92],"may":[94],"be":[96],"realistic":[97],"for":[98,114,169],"some":[99],"tasks":[100],"humanoid":[103],"balancing":[105],"locomotion.":[107],"This":[108],"paper":[109],"presents":[110],"an":[111],"iterative":[112,159],"approach":[113,160],"learning":[115,130],"models":[117],"optimizing":[119],"with":[121],"few":[123],"experiments":[125],"possible.":[127],"Instead":[128],"scratch,":[134],"our":[135],"method":[136],"learns":[137],"difference":[139],"between":[140],"hardware.":[145],"We":[146],"then":[147],"optimize":[148],"policy":[150],"based":[151],"learned":[154],"simulation.":[157],"The":[158],"allows":[161],"us":[162],"collect":[164],"wider":[165],"range":[166],"data":[168],"refinement":[171],"while":[172],"improving":[173],"policy.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}