{"id":"https://openalex.org/W4390481105","doi":"https://doi.org/10.1109/humanoids57100.2023.10375212","title":"Integrating Multi-Demonstration Knowledge and Bounded Workspaces for Efficient Deep Reinforcement Learning","display_name":"Integrating Multi-Demonstration Knowledge and Bounded Workspaces for Efficient Deep Reinforcement Learning","publication_year":2023,"publication_date":"2023-12-12","ids":{"openalex":"https://openalex.org/W4390481105","doi":"https://doi.org/10.1109/humanoids57100.2023.10375212"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids57100.2023.10375212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids57100.2023.10375212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE-RAS 22nd International Conference on Humanoid Robots (Humanoids)","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/A5036967034","display_name":"Ali Aflakian","orcid":"https://orcid.org/0000-0001-9777-7067"},"institutions":[{"id":"https://openalex.org/I4210156703","display_name":"The Faraday Institution","ror":"https://ror.org/05dt4bt98","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210156703"]},{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ali Aflakian","raw_affiliation_strings":["University of Birmingham,Department of Metallurgy & Materials Science,Birmingham,B15 2TT","Quad One, Harwell Science and Innovation Campus, The Faraday Institution, Didcot, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Birmingham,Department of Metallurgy & Materials Science,Birmingham,B15 2TT","institution_ids":["https://openalex.org/I79619799"]},{"raw_affiliation_string":"Quad One, Harwell Science and Innovation Campus, The Faraday Institution, Didcot, UK","institution_ids":["https://openalex.org/I4210156703"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005183926","display_name":"Rustam Stolkin","orcid":"https://orcid.org/0000-0002-0890-8836"},"institutions":[{"id":"https://openalex.org/I4210156703","display_name":"The Faraday Institution","ror":"https://ror.org/05dt4bt98","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210156703"]},{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rustam Stolkin","raw_affiliation_strings":["University of Birmingham,Department of Metallurgy & Materials Science,Birmingham,B15 2TT","Quad One, Harwell Science and Innovation Campus, The Faraday Institution, Didcot, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Birmingham,Department of Metallurgy & Materials Science,Birmingham,B15 2TT","institution_ids":["https://openalex.org/I79619799"]},{"raw_affiliation_string":"Quad One, Harwell Science and Innovation Campus, The Faraday Institution, Didcot, UK","institution_ids":["https://openalex.org/I4210156703"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046019885","display_name":"Alireza Rastegarpanah","orcid":"https://orcid.org/0000-0003-4264-6857"},"institutions":[{"id":"https://openalex.org/I4210156703","display_name":"The Faraday Institution","ror":"https://ror.org/05dt4bt98","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210156703"]},{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alireza Rastegarpanah","raw_affiliation_strings":["University of Birmingham,Department of Metallurgy & Materials Science,Birmingham,B15 2TT","Quad One, Harwell Science and Innovation Campus, The Faraday Institution, Didcot, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Birmingham,Department of Metallurgy & Materials Science,Birmingham,B15 2TT","institution_ids":["https://openalex.org/I79619799"]},{"raw_affiliation_string":"Quad One, Harwell Science and Innovation Campus, The Faraday Institution, Didcot, UK","institution_ids":["https://openalex.org/I4210156703"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3379,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.90513119,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994999766349792,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.8209326863288879},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6954790353775024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6893325448036194},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5483898520469666},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5384680032730103},{"id":"https://openalex.org/keywords/workspace","display_name":"Workspace","score":0.530426025390625},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4538097381591797},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4529713988304138},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44477343559265137},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.333156943321228},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14261963963508606},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09369057416915894}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8209326863288879},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6954790353775024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6893325448036194},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5483898520469666},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5384680032730103},{"id":"https://openalex.org/C58581272","wikidata":"https://www.wikidata.org/wiki/Q12741163","display_name":"Workspace","level":3,"score":0.530426025390625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4538097381591797},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4529713988304138},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44477343559265137},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.333156943321228},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14261963963508606},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09369057416915894},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/humanoids57100.2023.10375212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids57100.2023.10375212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE-RAS 22nd International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2153504150","https://openalex.org/W2788862220","https://openalex.org/W2962787969","https://openalex.org/W2963277051","https://openalex.org/W3009593063","https://openalex.org/W3038150710","https://openalex.org/W3038822267","https://openalex.org/W3128707967","https://openalex.org/W3138984732","https://openalex.org/W3183192539","https://openalex.org/W4286253093","https://openalex.org/W4319453704","https://openalex.org/W4383066631","https://openalex.org/W4386293535","https://openalex.org/W4394667800","https://openalex.org/W6638018090","https://openalex.org/W6718092244","https://openalex.org/W6849433528"],"related_works":["https://openalex.org/W1992503747","https://openalex.org/W2371519816","https://openalex.org/W2043154226","https://openalex.org/W2369529107","https://openalex.org/W2329043542","https://openalex.org/W2109948066","https://openalex.org/W1678858522","https://openalex.org/W3195090107","https://openalex.org/W2171197263","https://openalex.org/W2374577476"],"abstract_inverted_index":{"We":[0,35,84],"propose":[1],"a":[2,100],"novel":[3],"approach":[4,19,98,108,126,146],"for":[5,81],"boosting":[6],"deep":[7,156],"Reinforcement":[8],"Learning":[9],"(RL)":[10],"using":[11],"human":[12,24],"demonstrations":[13,25],"and":[14,32,53,89,119,165],"offline":[15],"workspace":[16],"bounding.":[17],"Our":[18,145],"involves":[20],"collecting":[21],"data":[22],"from":[23],"on":[26],"random":[27],"surfaces":[28],"with":[29,99,127],"varying":[30],"friction":[31],"stiffness":[33],"properties.":[34],"then":[36],"compute":[37],"a$3D$convex":[38],"hull":[39],"that":[40,106],"encompasses":[41],"all":[42],"the":[43,47,51,54,62,72,77,82,86,90,93,116,131,143,148,153],"paths":[44],"taken":[45],"by":[46],"demonstrators.":[48],"By":[49],"defining":[50],"task":[52],"desired":[55],"parameters":[56],"as":[57,136],"reward":[58],"functions,":[59],"we":[60],"enable":[61],"reinforcement":[63],"learning":[64,112],"agent":[65],"to":[66,121,150],"learn":[67],"an":[68],"optimal":[69],"solution":[70],"within":[71],"bounded":[73],"space,":[74],"significantly":[75,151],"reducing":[76],"search":[78],"space":[79],"required":[80],"agent.":[83],"compare":[85],"training":[87],"progress":[88],"behavior":[91,138],"of":[92,96,133,155],"trained":[94],"policy":[95],"our":[97,107,125],"baseline":[101],"approach.":[102],"The":[103],"results":[104],"demonstrate":[105],"not":[109],"only":[110],"expedites":[111],"but":[113],"also":[114,129],"improves":[115],"policy's":[117],"performance":[118],"resilience":[120],"local":[122],"minima.":[123],"Combining":[124],"RL":[128,157],"enables":[130],"use":[132],"imperfect":[134],"demonstrators":[135],"their":[137],"can":[139],"be":[140],"improved":[141],"during":[142],"learning.":[144],"has":[147],"potential":[149],"boost":[152],"development":[154],"applications":[158],"in":[159],"various":[160],"domains,":[161],"including":[162],"robotics,":[163],"gaming,":[164],"autonomous":[166],"systems.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}