{"id":"https://openalex.org/W2979229105","doi":"https://doi.org/10.1109/devlrn.2019.8850705","title":"Hindsight Experience Replay With Experience Ranking","display_name":"Hindsight Experience Replay With Experience Ranking","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2979229105","doi":"https://doi.org/10.1109/devlrn.2019.8850705","mag":"2979229105"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2019.8850705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2019.8850705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","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/A5037305946","display_name":"Van\u2010Dinh Nguyen","orcid":"https://orcid.org/0000-0002-9575-1063"},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hai Nguyen","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Nevada, Reno, NV, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Nevada, Reno, NV, USA","institution_ids":["https://openalex.org/I134113660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060555317","display_name":"Hung Manh La","orcid":"https://orcid.org/0000-0003-2183-2634"},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hung Manh La","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Nevada, Reno, NV, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Nevada, Reno, NV, USA","institution_ids":["https://openalex.org/I134113660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068594929","display_name":"Matthew Deans","orcid":null},"institutions":[{"id":"https://openalex.org/I1280536761","display_name":"Ames Research Center","ror":"https://ror.org/02acart68","country_code":"US","type":"facility","lineage":["https://openalex.org/I1280536761","https://openalex.org/I4210124779"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Deans","raw_affiliation_strings":["Intelligent Robotics Group, NASA Ames Research Center, Moffett Field, CA, USA"],"affiliations":[{"raw_affiliation_string":"Intelligent Robotics Group, NASA Ames Research Center, Moffett Field, CA, USA","institution_ids":["https://openalex.org/I1280536761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037305946"],"corresponding_institution_ids":["https://openalex.org/I134113660"],"apc_list":null,"apc_paid":null,"fwci":1.7471,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.88964268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973999857902527,"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":0.9973999857902527,"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/T13283","display_name":"Mental Health Research Topics","score":0.9836999773979187,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13219","display_name":"Mind wandering and attention","score":0.9782000184059143,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.9487122893333435},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7422130107879639},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.654235303401947},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6498026251792908},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6314727067947388},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5927630662918091},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.580257773399353},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.56564861536026},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3493770956993103},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.09041741490364075},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08328866958618164}],"concepts":[{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.9487122893333435},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7422130107879639},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.654235303401947},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6498026251792908},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6314727067947388},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5927630662918091},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.580257773399353},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.56564861536026},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3493770956993103},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.09041741490364075},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08328866958618164},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/devlrn.2019.8850705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2019.8850705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","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":30,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1900041959","https://openalex.org/W1967456522","https://openalex.org/W1974367810","https://openalex.org/W2042882799","https://openalex.org/W2062205907","https://openalex.org/W2100235553","https://openalex.org/W2139053308","https://openalex.org/W2141559645","https://openalex.org/W2143853187","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2201581102","https://openalex.org/W2789008106","https://openalex.org/W2930863966","https://openalex.org/W2935588605","https://openalex.org/W2963095800","https://openalex.org/W2963477884","https://openalex.org/W2963864421","https://openalex.org/W2964001908","https://openalex.org/W3037207827","https://openalex.org/W4293872189","https://openalex.org/W4298857966","https://openalex.org/W4300799055","https://openalex.org/W6637967152","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6730111887","https://openalex.org/W6740801417","https://openalex.org/W6748599296"],"related_works":["https://openalex.org/W3197854638","https://openalex.org/W3140454661","https://openalex.org/W4245029315","https://openalex.org/W1492315459","https://openalex.org/W1512434910","https://openalex.org/W2540910169","https://openalex.org/W3148904318","https://openalex.org/W2139970489","https://openalex.org/W2022803902","https://openalex.org/W2105474389"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"algorithms":[3],"face":[4],"difficulties":[5],"when":[6,58],"dealing":[7],"with":[8,25,85,93,139],"robotic":[9,181],"tasks":[10],"in":[11,56,143,173,178,189],"sparse":[12],"reward":[13],"settings":[14],"and":[15,48,130,134,162,195],"as":[16],"a":[17,140,148],"result,":[18],"they":[19],"often":[20],"require":[21],"millions":[22],"of":[23,78,103,191],"interactions":[24],"the":[26,52,59,64,86,94,100,131,137,145,156,163,169,192],"environment":[27],"to":[28,40,99,119,155],"learn":[29],"successfully.":[30],"A":[31],"recent":[32],"algorithm":[33],"Hindsight":[34],"Experience":[35],"Replay":[36],"(HER)":[37],"was":[38],"introduced":[39],"tackle":[41],"this":[42,108,112],"difficulty":[43],"by":[44,54,114],"adding":[45],"virtual":[46,105,128,149],"goals":[47,70],"therefore":[49],"increase":[50],"significantly":[51],"sample-efficiency":[53],"learning":[55,92,174,193],"transitions":[57],"robot":[60,146],"does":[61],"not":[62,153],"achieve":[63],"original":[65,87,95,132,157],"goal.":[66,88],"However,":[67],"these":[68,120],"additional":[69,121],"are":[71,159,165],"sampled":[72,127],"randomly":[73],"from":[74],"each":[75,126],"episode":[76],"batch":[77],"transitions,":[79],"which":[80,144],"might":[81,90],"have":[82],"no":[83],"relationship":[84],"This":[89],"make":[91],"goal":[96,129,133,150,158],"slower":[97],"due":[98],"bad":[101],"influence":[102],"irrelevant":[104],"goals.":[106,122],"In":[107],"paper,":[109],"we":[110],"address":[111],"issue":[113],"applying":[115],"experience":[116],"ranking":[117],"(ER)":[118],"We":[123],"first":[124],"compare":[125,136],"then":[135],"difference":[138],"threshold.":[141],"Transitions":[142],"achieves":[147],"that":[151],"is":[152,176],"close":[154],"filtered":[160],"out,":[161],"remaining":[164],"used":[166],"for":[167],"training":[168],"policy.":[170],"The":[171,183],"improvement":[172,188],"performance":[175],"validated":[177],"four":[179],"simulated":[180],"tasks.":[182],"experiment":[184],"results":[185],"show":[186],"significant":[187],"terms":[190],"speed":[194],"robustness.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}