{"id":"https://openalex.org/W4399768983","doi":"https://doi.org/10.1109/icara60736.2024.10553128","title":"Learning and Reusing Primitive Behaviours to Improve Hindsight Experience Replay Sample Efficiency","display_name":"Learning and Reusing Primitive Behaviours to Improve Hindsight Experience Replay Sample Efficiency","publication_year":2024,"publication_date":"2024-02-22","ids":{"openalex":"https://openalex.org/W4399768983","doi":"https://doi.org/10.1109/icara60736.2024.10553128"},"language":"en","primary_location":{"id":"doi:10.1109/icara60736.2024.10553128","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icara60736.2024.10553128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 10th International Conference on Automation, Robotics and Applications (ICARA)","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/A5005226665","display_name":"Francisco Rold\u00e1n S\u00e1nchez","orcid":"https://orcid.org/0009-0001-5954-0971"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Francisco Roldan Sanchez","raw_affiliation_strings":["Dublin City University,Insight SFI Centre for Data Analytics,Dublin,Ireland","Insight SFI Centre for Data Analytics, Dublin City University, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Dublin City University,Insight SFI Centre for Data Analytics,Dublin,Ireland","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"Insight SFI Centre for Data Analytics, Dublin City University, Dublin, Ireland","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114422958","display_name":"Qiang Wang","orcid":"https://orcid.org/0000-0002-1445-755X"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Qiang Wang","raw_affiliation_strings":["University College Dublin,Dublin,Ireland","University College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"University College Dublin,Dublin,Ireland","institution_ids":["https://openalex.org/I100930933"]},{"raw_affiliation_string":"University College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074319083","display_name":"David C\u00f3rdova Bulens","orcid":"https://orcid.org/0000-0003-2466-7179"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"David Cordova Bulens","raw_affiliation_strings":["University College Dublin,Dublin,Ireland","University College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"University College Dublin,Dublin,Ireland","institution_ids":["https://openalex.org/I100930933"]},{"raw_affiliation_string":"University College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073924795","display_name":"Kevin McGuinness","orcid":"https://orcid.org/0000-0003-1336-6477"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Kevin McGuinness","raw_affiliation_strings":["Dublin City University,Insight SFI Centre for Data Analytics,Dublin,Ireland","Insight SFI Centre for Data Analytics, Dublin City University, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Dublin City University,Insight SFI Centre for Data Analytics,Dublin,Ireland","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"Insight SFI Centre for Data Analytics, Dublin City University, Dublin, Ireland","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013317847","display_name":"Stephen J. Redmond","orcid":"https://orcid.org/0000-0002-2630-5449"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]},{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Stephen J. Redmond","raw_affiliation_strings":["University College Dublin,Insight SFI Centre for Data Analytics,Dublin,Ireland","Insight SFI Centre for Data Analytics, University College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"University College Dublin,Insight SFI Centre for Data Analytics,Dublin,Ireland","institution_ids":["https://openalex.org/I42934936","https://openalex.org/I100930933"]},{"raw_affiliation_string":"Insight SFI Centre for Data Analytics, University College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106498523","display_name":"Noel E. O\u2019Connor","orcid":"https://orcid.org/0000-0002-4033-9135"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Noel E. O'Connor","raw_affiliation_strings":["Dublin City University,Insight SFI Centre for Data Analytics,Dublin,Ireland","Insight SFI Centre for Data Analytics, Dublin City University, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Dublin City University,Insight SFI Centre for Data Analytics,Dublin,Ireland","institution_ids":["https://openalex.org/I42934936"]},{"raw_affiliation_string":"Insight SFI Centre for Data Analytics, Dublin City University, Dublin, Ireland","institution_ids":["https://openalex.org/I42934936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005226665"],"corresponding_institution_ids":["https://openalex.org/I42934936"],"apc_list":null,"apc_paid":null,"fwci":0.3634,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56706725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"30","issue":null,"first_page":"328","last_page":"333"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10427","display_name":"Visual perception and processing mechanisms","score":0.972100019454956,"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"}},"topics":[{"id":"https://openalex.org/T10427","display_name":"Visual perception and processing mechanisms","score":0.972100019454956,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9688000082969666,"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/T10648","display_name":"Virtual Reality Applications and Impacts","score":0.9678000211715698,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.9547102451324463},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.7829313278198242},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6722651124000549},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6409984827041626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3794601261615753},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3433172106742859},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22169837355613708},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.2034100592136383},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08289608359336853}],"concepts":[{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.9547102451324463},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.7829313278198242},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6722651124000549},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6409984827041626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3794601261615753},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3433172106742859},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22169837355613708},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2034100592136383},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08289608359336853},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"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/icara60736.2024.10553128","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icara60736.2024.10553128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 10th International Conference on Automation, Robotics and Applications (ICARA)","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":25,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2088807940","https://openalex.org/W2131600418","https://openalex.org/W2201581102","https://openalex.org/W2930863966","https://openalex.org/W2950110427","https://openalex.org/W2965870268","https://openalex.org/W2970948392","https://openalex.org/W2973229164","https://openalex.org/W3041764008","https://openalex.org/W3093562775","https://openalex.org/W3125547903","https://openalex.org/W3169291081","https://openalex.org/W3175270462","https://openalex.org/W3175584021","https://openalex.org/W3198826682","https://openalex.org/W3200307746","https://openalex.org/W3204657926","https://openalex.org/W3212887262","https://openalex.org/W3213789840","https://openalex.org/W4287126489","https://openalex.org/W4293872189","https://openalex.org/W4300799055","https://openalex.org/W4320855469","https://openalex.org/W4377704939"],"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":{"Hindsight":[0],"Experience":[1],"Replay":[2],"(HER)":[3],"is":[4,124,205],"a":[5,88,128,135,186],"technique":[6],"used":[7],"in":[8,48,103,175,196],"reinforcement":[9],"learning":[10,44,116],"(RL)":[11],"that":[12,90,94],"has":[13],"proven":[14],"to":[15,24,63,69,75,99,105,138,147],"be":[16],"very":[17,64],"efficient":[18,170],"for":[19],"training":[20,66],"off-policy":[21],"RL-based":[22,41],"agents":[23,42,183],"solve":[25,100],"goal-based":[26],"robotic":[27],"manipulation":[28,178],"tasks":[29,102],"using":[30,79,134,191],"sparse":[31],"rewards.":[32],"Even":[33],"though":[34],"HER":[35,166],"improves":[36],"the":[37,59,70,107,149,153,182],"sample":[38,199],"efficiency":[39,200],"of":[40,72,172,198],"by":[43,127,152,161],"from":[45],"mistakes":[46],"made":[47],"past":[49],"experiences,":[50],"it":[51],"does":[52],"not":[53,125,146],"provide":[54],"any":[55],"guidance":[56],"while":[57,115],"exploring":[58],"environment.":[60],"This":[61,121],"leads":[62],"large":[65],"times":[67],"due":[68],"volume":[71],"experience":[73],"required":[74],"train":[76],"an":[77],"agent":[78,108],"this":[80,84,173],"replay":[81],"strategy.":[82],"In":[83],"paper,":[85],"we":[86],"propose":[87],"method":[89,160],"uses":[91],"primitive":[92,155],"behaviours":[93],"have":[95],"been":[96],"previously":[97],"learned":[98],"simple":[101],"order":[104],"guide":[106],"toward":[109],"more":[110,118,169],"rewarding":[111],"actions":[112,150],"during":[113],"exploration":[114],"other":[117,168],"complex":[119],"tasks.":[120,179],"guidance,":[122],"however,":[123],"executed":[126],"manually":[129],"designed":[130],"curriculum,":[131],"but":[132],"rather":[133],"critic":[136],"network":[137],"decide":[139],"at":[140,207],"each":[141],"time":[142],"step":[143],"whether":[144],"or":[145],"use":[148],"proposed":[151,193],"previously-learned":[154],"policies.":[156],"We":[157,180],"evaluate":[158],"our":[159,192],"comparing":[162],"its":[163],"performance":[164],"against":[165],"and":[167,201],"variations":[171],"algorithm":[174],"several":[176],"block":[177],"demonstrate":[181],"can":[184],"learn":[185],"successful":[187],"policy":[188],"faster":[189],"when":[190],"method,":[194],"both":[195],"terms":[197],"computation":[202],"time.":[203],"Code":[204],"available":[206],"https://github.com/franroldans/qmp-her.":[208]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
