{"id":"https://openalex.org/W3094427810","doi":"https://doi.org/10.1109/ro-man47096.2020.9223473","title":"Goal Density-based Hindsight Experience Prioritization for Multi-Goal Robot Manipulation Reinforcement Learning","display_name":"Goal Density-based Hindsight Experience Prioritization for Multi-Goal Robot Manipulation Reinforcement Learning","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3094427810","doi":"https://doi.org/10.1109/ro-man47096.2020.9223473","mag":"3094427810"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man47096.2020.9223473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man47096.2020.9223473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","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/A5110888996","display_name":"Yingyi Kuang","orcid":null},"institutions":[{"id":"https://openalex.org/I169199633","display_name":"Aston University","ror":"https://ror.org/05j0ve876","country_code":"GB","type":"education","lineage":["https://openalex.org/I169199633"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yingyi Kuang","raw_affiliation_strings":["Aston Robotics, Vision and Intelligent Systems Lab (ARVIS), School of Engineering and Applied Science, Aston University, Birmingham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aston Robotics, Vision and Intelligent Systems Lab (ARVIS), School of Engineering and Applied Science, Aston University, Birmingham, UK","institution_ids":["https://openalex.org/I169199633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037956466","display_name":"Abraham Itzhak Weinberg","orcid":"https://orcid.org/0000-0002-2505-9653"},"institutions":[{"id":"https://openalex.org/I169199633","display_name":"Aston University","ror":"https://ror.org/05j0ve876","country_code":"GB","type":"education","lineage":["https://openalex.org/I169199633"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Abraham Itzhak Weinberg","raw_affiliation_strings":["Aston Robotics, Vision and Intelligent Systems Lab (ARVIS), School of Engineering and Applied Science, Aston University, Birmingham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aston Robotics, Vision and Intelligent Systems Lab (ARVIS), School of Engineering and Applied Science, Aston University, Birmingham, UK","institution_ids":["https://openalex.org/I169199633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020722131","display_name":"George Vogiatzis","orcid":"https://orcid.org/0000-0002-3226-0603"},"institutions":[{"id":"https://openalex.org/I169199633","display_name":"Aston University","ror":"https://ror.org/05j0ve876","country_code":"GB","type":"education","lineage":["https://openalex.org/I169199633"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"George Vogiatzis","raw_affiliation_strings":["Aston Robotics, Vision and Intelligent Systems Lab (ARVIS), School of Engineering and Applied Science, Aston University, Birmingham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aston Robotics, Vision and Intelligent Systems Lab (ARVIS), School of Engineering and Applied Science, Aston University, Birmingham, UK","institution_ids":["https://openalex.org/I169199633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032454100","display_name":"Diego R. Faria","orcid":"https://orcid.org/0000-0002-2771-1713"},"institutions":[{"id":"https://openalex.org/I169199633","display_name":"Aston University","ror":"https://ror.org/05j0ve876","country_code":"GB","type":"education","lineage":["https://openalex.org/I169199633"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Diego R. Faria","raw_affiliation_strings":["Aston Robotics, Vision and Intelligent Systems Lab (ARVIS), School of Engineering and Applied Science, Aston University, Birmingham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aston Robotics, Vision and Intelligent Systems Lab (ARVIS), School of Engineering and Applied Science, Aston University, Birmingham, UK","institution_ids":["https://openalex.org/I169199633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110888996"],"corresponding_institution_ids":["https://openalex.org/I169199633"],"apc_list":null,"apc_paid":null,"fwci":0.952,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.8148819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"432","last_page":"437"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9591000080108643,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.9542122483253479},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8254467248916626},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7725167274475098},{"id":"https://openalex.org/keywords/prioritization","display_name":"Prioritization","score":0.6890522837638855},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.644085168838501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6312158703804016},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6062910556793213},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5844085216522217},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5754109621047974},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.46809911727905273},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10030034184455872},{"id":"https://openalex.org/keywords/process-management","display_name":"Process management","score":0.08295175433158875}],"concepts":[{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.9542122483253479},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8254467248916626},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7725167274475098},{"id":"https://openalex.org/C2777615720","wikidata":"https://www.wikidata.org/wiki/Q11888847","display_name":"Prioritization","level":2,"score":0.6890522837638855},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.644085168838501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6312158703804016},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6062910556793213},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5844085216522217},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5754109621047974},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.46809911727905273},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10030034184455872},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.08295175433158875},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"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/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man47096.2020.9223473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man47096.2020.9223473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G5542537536","display_name":null,"funder_award_id":"EP/S032355/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W606806978","https://openalex.org/W2158782408","https://openalex.org/W2201581102","https://openalex.org/W2575705757","https://openalex.org/W2610395436","https://openalex.org/W2789008106","https://openalex.org/W2905606790","https://openalex.org/W2930863966","https://openalex.org/W2945282704","https://openalex.org/W2946723315","https://openalex.org/W2962945224","https://openalex.org/W2963477884","https://openalex.org/W2963864421","https://openalex.org/W2964001908","https://openalex.org/W2970948392","https://openalex.org/W2979229105","https://openalex.org/W2990747716","https://openalex.org/W4288356606","https://openalex.org/W4293872189","https://openalex.org/W4300799055","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6737327832","https://openalex.org/W6740801417","https://openalex.org/W6748599296","https://openalex.org/W6755289019","https://openalex.org/W6757438168","https://openalex.org/W6762477786","https://openalex.org/W6762640273","https://openalex.org/W6763356705"],"related_works":["https://openalex.org/W3197854638","https://openalex.org/W3140454661","https://openalex.org/W4245029315","https://openalex.org/W2139970489","https://openalex.org/W1492315459","https://openalex.org/W1512434910","https://openalex.org/W2540910169","https://openalex.org/W3012552522","https://openalex.org/W2903025760","https://openalex.org/W4289147272"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,39,100,173,193],"for":[2,95,142],"multi-goal":[3],"robot":[4],"manipulation":[5,184],"tasks":[6,197],"is":[7,27,68,83],"usually":[8],"challenging,":[9],"especially":[10],"when":[11,202],"sparse":[12],"rewards":[13],"are":[14,128,137],"provided.":[15],"It":[16],"often":[17],"requires":[18],"millions":[19],"of":[20,50,63,119],"data":[21],"collected":[22],"before":[23],"a":[24],"stable":[25],"strategy":[26,94],"learned.":[28],"Recent":[29],"algorithms":[30,161],"like":[31],"Hindsight":[32],"Experience":[33],"Replay":[34],"(HER)":[35],"have":[36],"accelerated":[37],"the":[38,44,51,57,61,75,79,99,104,116,120,132,168,192],"process":[40,194],"greatly":[41],"by":[42],"replacing":[43],"original":[45],"desired":[46],"goal":[47,81],"with":[48,151,179,204],"one":[49],"achieved":[52,121,125],"points":[53,122,126,136],"(substitute":[54],"goals)":[55],"alongside":[56],"same":[58],"trajectory.":[59],"However,":[60],"selection":[62,77],"previous":[64],"experience":[65,92,108,159],"to":[66,156,166],"learn":[67],"naively":[69],"sampled":[70],"in":[71,73,131,195],"HER,":[72],"which":[74,127,164],"trajectory":[76],"and":[78,123,198],"substitute":[80,140],"sampling":[82],"completely":[84],"random.":[85],"In":[86,144],"this":[87],"paper,":[88],"we":[89,146],"discuss":[90],"an":[91,148],"prioritization":[93,160,206],"HER":[96],"that":[97,112,189],"improves":[98],"efficiency.":[101],"We":[102,175],"propose":[103,147],"Goal":[105],"Density-based":[106],"hindsight":[107],"Prioritization":[109,149],"(GDP)":[110],"method":[111,155,178],"focuses":[113],"on":[114],"utilizing":[115],"density":[117],"distribution":[118],"prioritizes":[124],"rarely":[129],"seen":[130],"replay":[133],"buffer.":[134],"These":[135],"used":[138],"as":[139],"goals":[141],"HER.":[143],"addition,":[145],"Switching":[150],"Ensembling":[152],"Strategy":[153],"(PSES)":[154],"switch":[157],"different":[158],"during":[162,171],"learning,":[163],"allows":[165],"select":[167],"best":[169],"performance":[170],"each":[172],"stage.":[174],"evaluate":[176],"our":[177],"several":[180],"OpenAI":[181],"Gym":[182],"robotic":[183],"tasks.":[185],"The":[186],"results":[187],"show":[188],"GDP":[190],"accelerates":[191],"most":[196],"can":[199],"be":[200],"improved":[201],"combining":[203],"other":[205],"methods":[207],"using":[208],"PSES.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}