{"id":"https://openalex.org/W4317792690","doi":"https://doi.org/10.1109/wsc57314.2022.10015308","title":"Accelerating Training of Reinforcement Learning-Based Construction Robots in Simulation Using Demonstrations Collected in Virtual Reality","display_name":"Accelerating Training of Reinforcement Learning-Based Construction Robots in Simulation Using Demonstrations Collected in Virtual Reality","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4317792690","doi":"https://doi.org/10.1109/wsc57314.2022.10015308"},"language":"en","primary_location":{"id":"doi:10.1109/wsc57314.2022.10015308","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/wsc57314.2022.10015308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Winter Simulation Conference (WSC)","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/A5100784431","display_name":"Lei Huang","orcid":"https://orcid.org/0000-0003-4760-7064"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Lei Huang","raw_affiliation_strings":["University of British Columbia,Department of Civil Engineering,Vancouver,BC,CANADA,V6T 1Z4"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia,Department of Civil Engineering,Vancouver,BC,CANADA,V6T 1Z4","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001924431","display_name":"Zhengbo Zou","orcid":"https://orcid.org/0000-0002-7789-655X"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhengbo Zou","raw_affiliation_strings":["University of British Columbia,Department of Civil Engineering,Vancouver,BC,CANADA,V6T 1Z4"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia,Department of Civil Engineering,Vancouver,BC,CANADA,V6T 1Z4","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31620848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"2451","last_page":"2462"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11006","display_name":"BIM and Construction Integration","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11006","display_name":"BIM and Construction Integration","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T12190","display_name":"Innovations in Concrete and Construction Materials","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9555000066757202,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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":0.8506530523300171},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7799886465072632},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7491228580474854},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.7122511267662048},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6678287982940674},{"id":"https://openalex.org/keywords/economic-shortage","display_name":"Economic shortage","score":0.5899895429611206},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5076411962509155},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.4930431544780731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4595000743865967},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.32279422879219055},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17969706654548645},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.09391191601753235}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8506530523300171},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7799886465072632},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7491228580474854},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.7122511267662048},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6678287982940674},{"id":"https://openalex.org/C194051981","wikidata":"https://www.wikidata.org/wiki/Q1337691","display_name":"Economic shortage","level":3,"score":0.5899895429611206},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5076411962509155},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.4930431544780731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4595000743865967},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.32279422879219055},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17969706654548645},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09391191601753235},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wsc57314.2022.10015308","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/wsc57314.2022.10015308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Winter Simulation Conference (WSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"},{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W244727899","https://openalex.org/W1738827650","https://openalex.org/W1964173900","https://openalex.org/W1973674690","https://openalex.org/W1984814029","https://openalex.org/W1993395669","https://openalex.org/W2134911466","https://openalex.org/W2559317869","https://openalex.org/W2565736833","https://openalex.org/W2607662938","https://openalex.org/W2736601468","https://openalex.org/W2741122588","https://openalex.org/W2747329762","https://openalex.org/W2799151646","https://openalex.org/W2800751821","https://openalex.org/W2802859884","https://openalex.org/W2888248460","https://openalex.org/W2896596112","https://openalex.org/W2911311605","https://openalex.org/W2921144593","https://openalex.org/W2955601128","https://openalex.org/W2963411833","https://openalex.org/W2963802910","https://openalex.org/W3046774844","https://openalex.org/W3105894518","https://openalex.org/W3126321819","https://openalex.org/W3133270427","https://openalex.org/W3133805463","https://openalex.org/W3188255222","https://openalex.org/W3210516907","https://openalex.org/W4212774754","https://openalex.org/W4214717370","https://openalex.org/W4230995140","https://openalex.org/W4293363567","https://openalex.org/W6638018090","https://openalex.org/W6741002519","https://openalex.org/W6742461812","https://openalex.org/W6748554570","https://openalex.org/W6748839928","https://openalex.org/W6750186571","https://openalex.org/W6752089545","https://openalex.org/W6752165109","https://openalex.org/W6779827379","https://openalex.org/W6800456564","https://openalex.org/W6804244202"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W2509147714","https://openalex.org/W4380318855","https://openalex.org/W2579473328","https://openalex.org/W2138720691","https://openalex.org/W46955353","https://openalex.org/W2031695474","https://openalex.org/W4239898203","https://openalex.org/W2955295882"],"abstract_inverted_index":{"The":[0],"application":[1],"of":[2,44,57,79,91,105,144],"construction":[3,13,59,80,99,147],"robots":[4,26,38,145],"is":[5,49],"crucial":[6],"to":[7,27,40,51,74,117],"mitigate":[8],"challenges":[9],"faced":[10],"by":[11,130],"the":[12,54,76,86,89,123,142],"industry,":[14],"such":[15],"as":[16],"labor":[17],"shortages":[18],"and":[19,94],"low":[20],"productivity.":[21],"Reinforcement":[22],"learning":[23,146],"(RL)":[24],"enables":[25],"take":[28],"actions":[29],"based":[30],"on":[31,96],"observed":[32],"states,":[33],"improving":[34],"flexibility":[35],"over":[36],"traditional":[37],"pre-programmed":[39],"follow":[41],"determined":[42],"sequences":[43],"instructions.":[45],"However,":[46],"RL-based":[47,58],"control":[48],"time-consuming":[50],"train,":[52],"hindering":[53],"wide":[55],"adoption":[56],"robots.":[60,81],"This":[61],"paper":[62],"proposes":[63],"an":[64,118],"approach":[65,87],"that":[66],"utilizes":[67],"expert":[68,112,137],"demonstrations":[69,129,138],"collected":[70],"from":[71],"virtual":[72,98,111],"reality":[73],"accelerate":[75,141],"RL":[77,107,125],"training":[78,143],"For":[82],"evaluation,":[83],"we":[84],"implement":[85],"for":[88],"task":[90],"window":[92],"pickup":[93],"installation":[95],"a":[97],"site.":[100],"In":[101],"our":[102],"experiment,":[103],"out":[104],"10":[106],"agents":[108,115],"trained":[109,127],"using":[110],"demonstrations,":[113],"7":[114],"converge":[116],"optimal":[119],"policy":[120],"faster":[121],"than":[122],"baseline":[124],"agent":[126],"without":[128],"around":[131],"40":[132],"epochs,":[133],"which":[134],"proves":[135],"adding":[136],"can":[139],"effectively":[140],"tasks.":[148]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
