{"id":"https://openalex.org/W3141423234","doi":"https://doi.org/10.1109/access.2021.3069975","title":"Hindsight Goal Ranking on Replay Buffer for Sparse Reward Environment","display_name":"Hindsight Goal Ranking on Replay Buffer for Sparse Reward Environment","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3141423234","doi":"https://doi.org/10.1109/access.2021.3069975","mag":"3141423234"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3069975","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3069975","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09391700.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09391700.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028393159","display_name":"Tung M. Luu","orcid":"https://orcid.org/0000-0001-9488-7463"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Tung M. Luu","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-9488-7463","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073287748","display_name":"Chang D. Yoo","orcid":"https://orcid.org/0000-0002-0756-7179"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chang D. Yoo","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-0756-7179","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028393159"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.6996,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.75423243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"9","issue":null,"first_page":"51996","last_page":"52007"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.9879000186920166,"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":0.9695000052452087,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.9925740957260132},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7274193167686462},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6395817399024963},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.609893798828125},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.546708345413208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4921666979789734},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4178747534751892},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13821813464164734},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.1356065571308136},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07487985491752625}],"concepts":[{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.9925740957260132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7274193167686462},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6395817399024963},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.609893798828125},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.546708345413208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4921666979789734},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4178747534751892},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13821813464164734},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.1356065571308136},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07487985491752625},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2021.3069975","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3069975","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09391700.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2110.15043","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.15043","pdf_url":"https://arxiv.org/pdf/2110.15043","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:941a38c240a4458bacb728aa0ad7e1b9","is_oa":true,"landing_page_url":"https://doaj.org/article/941a38c240a4458bacb728aa0ad7e1b9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 51996-52007 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3069975","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3069975","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09391700.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1478646649","display_name":null,"funder_award_id":"2019-0-01396","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G2476533896","display_name":null,"funder_award_id":"2019-0-01396","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3141423234.pdf","grobid_xml":"https://content.openalex.org/works/W3141423234.grobid-xml"},"referenced_works_count":92,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W567721252","https://openalex.org/W1522301498","https://openalex.org/W1757796397","https://openalex.org/W1949804828","https://openalex.org/W2108734173","https://openalex.org/W2121863487","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2155968351","https://openalex.org/W2158782408","https://openalex.org/W2159420891","https://openalex.org/W2165150801","https://openalex.org/W2167224731","https://openalex.org/W2173248099","https://openalex.org/W2173564293","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2342662072","https://openalex.org/W2616430965","https://openalex.org/W2744921630","https://openalex.org/W2746553466","https://openalex.org/W2768498556","https://openalex.org/W2772709170","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2789008106","https://openalex.org/W2810785043","https://openalex.org/W2823112946","https://openalex.org/W2909335861","https://openalex.org/W2922007426","https://openalex.org/W2946723315","https://openalex.org/W2947638559","https://openalex.org/W2951799221","https://openalex.org/W2963003097","https://openalex.org/W2963099939","https://openalex.org/W2963277051","https://openalex.org/W2963293881","https://openalex.org/W2963311874","https://openalex.org/W2963477884","https://openalex.org/W2963484919","https://openalex.org/W2963641140","https://openalex.org/W2963864421","https://openalex.org/W2963923407","https://openalex.org/W2964001908","https://openalex.org/W2964121744","https://openalex.org/W2964161785","https://openalex.org/W2964342357","https://openalex.org/W2970377754","https://openalex.org/W3007848632","https://openalex.org/W3008970887","https://openalex.org/W3035717769","https://openalex.org/W4254755460","https://openalex.org/W4289440819","https://openalex.org/W4293872189","https://openalex.org/W4297795006","https://openalex.org/W4298857966","https://openalex.org/W4300799055","https://openalex.org/W4302570325","https://openalex.org/W6616173779","https://openalex.org/W6631190155","https://openalex.org/W6637967152","https://openalex.org/W6682849425","https://openalex.org/W6683452725","https://openalex.org/W6684205842","https://openalex.org/W6684338915","https://openalex.org/W6684921986","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6704571135","https://openalex.org/W6718092244","https://openalex.org/W6737937804","https://openalex.org/W6740801417","https://openalex.org/W6741302124","https://openalex.org/W6742667875","https://openalex.org/W6745747580","https://openalex.org/W6746177919","https://openalex.org/W6747473740","https://openalex.org/W6748599296","https://openalex.org/W6748839928","https://openalex.org/W6753060773","https://openalex.org/W6753243525","https://openalex.org/W6755289019","https://openalex.org/W6758315252","https://openalex.org/W6760560886","https://openalex.org/W6762640273","https://openalex.org/W6762868464","https://openalex.org/W6765008394","https://openalex.org/W6774784542","https://openalex.org/W6774967489","https://openalex.org/W6780559895"],"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/W3089780453","https://openalex.org/W3148904318","https://openalex.org/W2022803902"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,56],"method":[4,126],"for":[5,74,103],"prioritizing":[6],"the":[7,19,40,60,63,89,94,104,107],"replay":[8],"experience":[9],"referred":[10],"to":[11,93,111],"as":[12,55],"Hindsight":[13,22],"Goal":[14],"Ranking":[15],"(HGR)":[16],"in":[17,43,80],"overcoming":[18],"limitation":[20],"of":[21,59,98],"Experience":[23],"Replay":[24],"(HER)":[25],"that":[26,144,159],"generates":[27],"hindsight":[28,108],"goals":[29],"based":[30],"on":[31,39,148],"uniform":[32],"sampling.":[33],"HGR":[34,160],"samples":[35,162],"with":[36,46,117,128],"higher":[37,118],"probability":[38,119],"states":[41],"visited":[42,122],"an":[44,69,84,134],"episode":[45,85],"larger":[47,112],"temporal":[48],"difference":[49],"(TD)":[50],"error,":[51],"which":[52,62],"is":[53,78,86,115],"considered":[54],"proxy":[57],"measure":[58],"amount":[61],"RL":[64],"agent":[65],"can":[66],"learn":[67],"from":[68,88,120],"experience.":[70],"The":[71,124,155],"actual":[72],"sampling":[73],"large":[75],"TD":[76,96,113],"error":[77,97,114],"performed":[79],"two":[81],"steps:":[82],"first,":[83],"sampled":[87,105,116],"relay":[90],"buffer":[91],"according":[92],"average":[95],"its":[99],"experiences,":[100],"and":[101],"then,":[102],"episode,":[106],"goal":[109],"leading":[110],"future":[121],"states.":[123],"proposed":[125],"combined":[127],"Deep":[129],"Deterministic":[130],"Policy":[131],"Gradient":[132],"(DDPG),":[133],"off-policy":[135],"model-free":[136],"actor-critic":[137],"algorithm,":[138],"accelerates":[139],"learning":[140],"significantly":[141],"faster":[142],"than":[143,165],"without":[145],"any":[146],"prioritization":[147],"four":[149],"challenging":[150],"simulated":[151],"robotic":[152],"manipulation":[153],"tasks.":[154,170],"empirical":[156],"results":[157],"show":[158],"uses":[161],"more":[163],"efficiently":[164],"previous":[166],"methods":[167],"across":[168],"all":[169]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}