{"id":"https://openalex.org/W4400524645","doi":"https://doi.org/10.1109/access.2024.3427012","title":"HiER: Highlight Experience Replay for Boosting Off-Policy Reinforcement Learning Agents","display_name":"HiER: Highlight Experience Replay for Boosting Off-Policy Reinforcement Learning Agents","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400524645","doi":"https://doi.org/10.1109/access.2024.3427012"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3427012","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3427012","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3427012","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101802451","display_name":"D\u00e1niel Horv\u00e1th","orcid":"https://orcid.org/0000-0002-6450-5193"},"institutions":[{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]},{"id":"https://openalex.org/I4210117195","display_name":"Institute for Computer Science and Control","ror":"https://ror.org/0249v7n71","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210117195","https://openalex.org/I7597260"]},{"id":"https://openalex.org/I4210154688","display_name":"H\u00f4pital Saint-Michel","ror":"https://ror.org/057v2pg43","country_code":"FR","type":"healthcare","lineage":["https://openalex.org/I4210154688"]},{"id":"https://openalex.org/I4210156829","display_name":"Research Network (United States)","ror":"https://ror.org/04tgjxk96","country_code":"US","type":"company","lineage":["https://openalex.org/I4210156829"]},{"id":"https://openalex.org/I4387152226","display_name":"Hungarian Research Network","ror":"https://ror.org/04w6pnc49","country_code":"HU","type":"other","lineage":["https://openalex.org/I4387152226"]},{"id":"https://openalex.org/I4403386650","display_name":"Centre de Robotique","ror":"https://ror.org/0180r7w69","country_code":null,"type":"education","lineage":["https://openalex.org/I190752583","https://openalex.org/I2746051580","https://openalex.org/I4403386650","https://openalex.org/I70768539"]}],"countries":["FR","HU","US"],"is_corresponding":true,"raw_author_name":"D\u00e1niel Horv\u00e1th","raw_affiliation_strings":["Center for Robotics, Mines Paris, PSL University, Paris, France","Centre of Excellence in Production Informatics and Control, Institute for Computer Science and Control, Hungarian Research Network, Budapest (Hongrie)","CAOR - Centre de Robotique (60, boulevard Saint-Michel 75272 Paris cedex 06 - France)"],"affiliations":[{"raw_affiliation_string":"Center for Robotics, Mines Paris, PSL University, Paris, France","institution_ids":["https://openalex.org/I2746051580"]},{"raw_affiliation_string":"Centre of Excellence in Production Informatics and Control, Institute for Computer Science and Control, Hungarian Research Network, Budapest (Hongrie)","institution_ids":["https://openalex.org/I4210117195","https://openalex.org/I4210156829","https://openalex.org/I4387152226"]},{"raw_affiliation_string":"CAOR - Centre de Robotique (60, boulevard Saint-Michel 75272 Paris cedex 06 - France)","institution_ids":["https://openalex.org/I4210154688","https://openalex.org/I4403386650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103974307","display_name":"Jes\u00fas Bujalance Mart\u00edn","orcid":null},"institutions":[{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]},{"id":"https://openalex.org/I4210154688","display_name":"H\u00f4pital Saint-Michel","ror":"https://ror.org/057v2pg43","country_code":"FR","type":"healthcare","lineage":["https://openalex.org/I4210154688"]},{"id":"https://openalex.org/I4403386650","display_name":"Centre de Robotique","ror":"https://ror.org/0180r7w69","country_code":null,"type":"education","lineage":["https://openalex.org/I190752583","https://openalex.org/I2746051580","https://openalex.org/I4403386650","https://openalex.org/I70768539"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jes\u00fas Bujalance Mart\u00edn","raw_affiliation_strings":["Center for Robotics, Mines Paris, PSL University, Paris, France","CAOR - Centre de Robotique (60, boulevard Saint-Michel 75272 Paris cedex 06 - France)"],"affiliations":[{"raw_affiliation_string":"Center for Robotics, Mines Paris, PSL University, Paris, France","institution_ids":["https://openalex.org/I2746051580"]},{"raw_affiliation_string":"CAOR - Centre de Robotique (60, boulevard Saint-Michel 75272 Paris cedex 06 - France)","institution_ids":["https://openalex.org/I4210154688","https://openalex.org/I4403386650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032249136","display_name":"G\u00e1bor Erd\u0151s","orcid":"https://orcid.org/0000-0002-3531-3803"},"institutions":[{"id":"https://openalex.org/I4210117195","display_name":"Institute for Computer Science and Control","ror":"https://ror.org/0249v7n71","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210117195","https://openalex.org/I7597260"]},{"id":"https://openalex.org/I4210156829","display_name":"Research Network (United States)","ror":"https://ror.org/04tgjxk96","country_code":"US","type":"company","lineage":["https://openalex.org/I4210156829"]},{"id":"https://openalex.org/I4387152226","display_name":"Hungarian Research Network","ror":"https://ror.org/04w6pnc49","country_code":"HU","type":"other","lineage":["https://openalex.org/I4387152226"]}],"countries":["HU","US"],"is_corresponding":false,"raw_author_name":"Ferenc G\u00e0bor Erdos","raw_affiliation_strings":["Centre of Excellence in Production Informatics and Control, Institute for Computer Science and Control, Hungarian Research Network, Budapest, Hungary","Centre of Excellence in Production Informatics and Control, Institute for Computer Science and Control, Hungarian Research Network, Budapest (Hongrie)"],"affiliations":[{"raw_affiliation_string":"Centre of Excellence in Production Informatics and Control, Institute for Computer Science and Control, Hungarian Research Network, Budapest, Hungary","institution_ids":["https://openalex.org/I4387152226","https://openalex.org/I4210117195"]},{"raw_affiliation_string":"Centre of Excellence in Production Informatics and Control, Institute for Computer Science and Control, Hungarian Research Network, Budapest (Hongrie)","institution_ids":["https://openalex.org/I4210117195","https://openalex.org/I4210156829","https://openalex.org/I4387152226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053867332","display_name":"Zolt\u00e1n Istenes","orcid":"https://orcid.org/0000-0002-0169-4791"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zolt\u00e1n Istenes","raw_affiliation_strings":["CoLocation Center for Academic and Industrial Cooperation, E&#x00F6;tv&#x00F6;s Lor&#x00E1;nd University, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"CoLocation Center for Academic and Industrial Cooperation, E&#x00F6;tv&#x00F6;s Lor&#x00E1;nd University, Budapest, Hungary","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008228948","display_name":"Fabien Moutarde","orcid":"https://orcid.org/0000-0003-4799-7285"},"institutions":[{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]},{"id":"https://openalex.org/I4210154688","display_name":"H\u00f4pital Saint-Michel","ror":"https://ror.org/057v2pg43","country_code":"FR","type":"healthcare","lineage":["https://openalex.org/I4210154688"]},{"id":"https://openalex.org/I4403386650","display_name":"Centre de Robotique","ror":"https://ror.org/0180r7w69","country_code":null,"type":"education","lineage":["https://openalex.org/I190752583","https://openalex.org/I2746051580","https://openalex.org/I4403386650","https://openalex.org/I70768539"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fabien Moutarde","raw_affiliation_strings":["Center for Robotics, Mines Paris, PSL University, Paris, France","CAOR - Centre de Robotique (60, boulevard Saint-Michel 75272 Paris cedex 06 - France)"],"affiliations":[{"raw_affiliation_string":"Center for Robotics, Mines Paris, PSL University, Paris, France","institution_ids":["https://openalex.org/I2746051580"]},{"raw_affiliation_string":"CAOR - Centre de Robotique (60, boulevard Saint-Michel 75272 Paris cedex 06 - France)","institution_ids":["https://openalex.org/I4210154688","https://openalex.org/I4403386650"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101802451"],"corresponding_institution_ids":["https://openalex.org/I2746051580","https://openalex.org/I4210117195","https://openalex.org/I4210154688","https://openalex.org/I4210156829","https://openalex.org/I4387152226","https://openalex.org/I4403386650"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.0325,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79993284,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"12","issue":null,"first_page":"100102","last_page":"100119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"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":0.9976000189781189,"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/T13219","display_name":"Mind wandering and attention","score":0.9840999841690063,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9675999879837036,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.812538206577301},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8043688535690308},{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.7390663623809814},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6224806308746338},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5686637759208679},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5494267344474792},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4702310264110565},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46232014894485474},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3644647002220154},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3542305827140808},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3461172580718994},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08533209562301636}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.812538206577301},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8043688535690308},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.7390663623809814},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6224806308746338},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5686637759208679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5494267344474792},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4702310264110565},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46232014894485474},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3644647002220154},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3542305827140808},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3461172580718994},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08533209562301636},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/access.2024.3427012","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3427012","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-04657862v1","is_oa":true,"landing_page_url":"https://minesparis-psl.hal.science/hal-04657862","pdf_url":"https://minesparis-psl.hal.science/hal-04657862/document","source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, 2024, pp.1-1. &#x27E8;10.1109/ACCESS.2024.3427012&#x27E9;","raw_type":"Journal articles"},{"id":"pmh:oai:doaj.org/article:2aa566d34503416a996ac6f4741fa09d","is_oa":true,"landing_page_url":"https://doaj.org/article/2aa566d34503416a996ac6f4741fa09d","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 100102-100119 (2024)","raw_type":"article"},{"id":"pmh:oai:eprints.sztaki.hu:10775","is_oa":false,"landing_page_url":"https://eprints.sztaki.hu/10775/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401907","display_name":"SZTAKI Publication Repository (Hungarian Academy of Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I7597260","host_organization_name":"Hungarian Academy of Sciences","host_organization_lineage":["https://openalex.org/I7597260"],"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":"PeerReviewed"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3427012","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3427012","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1093125731","display_name":null,"funder_award_id":"RRF-2.3.1-21-2022-00004","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G3241820797","display_name":null,"funder_award_id":"RRF-2.3.1-21-2022-00004","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4937468798","display_name":null,"funder_award_id":"H2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7046074316","display_name":null,"funder_award_id":"739592","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8867200142","display_name":null,"funder_award_id":"739592","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G938802132","display_name":null,"funder_award_id":"RRF-2.3.1-21-2022-00004","funder_id":"https://openalex.org/F4320328860","funder_display_name":"Magyarorsz\u00e1g Korm\u00e1nya"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320323942","display_name":"Campus France","ror":"https://ror.org/04wtce741"},{"id":"https://openalex.org/F4320328860","display_name":"Magyarorsz\u00e1g Korm\u00e1nya","ror":"https://ror.org/007ekx298"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2158782408","https://openalex.org/W2165698076","https://openalex.org/W2201581102","https://openalex.org/W2296073425","https://openalex.org/W2395579298","https://openalex.org/W2424347275","https://openalex.org/W2603088459","https://openalex.org/W2616430965","https://openalex.org/W2754517384","https://openalex.org/W2766447205","https://openalex.org/W2772709170","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2804380964","https://openalex.org/W2809256243","https://openalex.org/W2904157920","https://openalex.org/W2948708918","https://openalex.org/W2963311874","https://openalex.org/W2963516811","https://openalex.org/W2963864421","https://openalex.org/W2967515482","https://openalex.org/W2968917487","https://openalex.org/W2970677506","https://openalex.org/W2975141838","https://openalex.org/W2994722919","https://openalex.org/W3005431655","https://openalex.org/W3016525976","https://openalex.org/W3035717769","https://openalex.org/W3040707741","https://openalex.org/W3041202696","https://openalex.org/W3089353688","https://openalex.org/W3090299930","https://openalex.org/W3099098707","https://openalex.org/W3115706066","https://openalex.org/W3142849873","https://openalex.org/W3206820790","https://openalex.org/W3212580602","https://openalex.org/W4210488105","https://openalex.org/W4214717370","https://openalex.org/W4287113380","https://openalex.org/W4288374418","https://openalex.org/W4293872189","https://openalex.org/W4307411952","https://openalex.org/W4388904942","https://openalex.org/W6616173779","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6735789912","https://openalex.org/W6737937804","https://openalex.org/W6740801417","https://openalex.org/W6741302124","https://openalex.org/W6746177919","https://openalex.org/W6747473740","https://openalex.org/W6748599296","https://openalex.org/W6748839928","https://openalex.org/W6751540476","https://openalex.org/W6752603789","https://openalex.org/W6757288412","https://openalex.org/W6760560886","https://openalex.org/W6761443123","https://openalex.org/W6762935222","https://openalex.org/W6768177389","https://openalex.org/W6774583691","https://openalex.org/W6775522024","https://openalex.org/W6776601253","https://openalex.org/W6787348534","https://openalex.org/W6800570120","https://openalex.org/W6810892028"],"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":{"Even":[0],"though":[1],"reinforcement-learning-based":[2],"algorithms":[3],"achieved":[4],"superhuman":[5],"performance":[6,117],"in":[7,51,140],"many":[8,34],"domains,":[9],"the":[10,18,26,36,71,76,79,85,88,100,116,119,132,155,165],"field":[11],"of":[12,40,45,102,118,125,135],"robotics":[13],"poses":[14],"significant":[15],"challenges":[16],"as":[17],"state":[19],"and":[20,25,87,107,158],"action":[21],"spaces":[22],"are":[23,81,162],"continuous,":[24],"reward":[27],"function":[28],"is":[29,38,143],"predominantly":[30],"sparse.":[31],"Furthermore,":[32,129],"on":[33,122,164],"occasions,":[35],"agent":[37],"devoid":[39],"access":[41],"to":[42,130],"any":[43],"form":[44],"demonstration.":[46],"Inspired":[47],"by":[48],"human":[49],"learning,":[50],"this":[52],"work,":[53],"we":[54,137],"propose":[55,138],"a":[56,65,159],"method":[57,113],"named":[58],"highlight":[59,67,89],"experience":[60,90,104,109],"replay":[61,68,91,105,110],"(HiER)":[62],"that":[63],"creates":[64],"secondary":[66],"buffer":[69],"for":[70],"most":[72],"relevant":[73],"experiences.":[74],"For":[75],"weights":[77],"update,":[78],"transitions":[80],"sampled":[82],"from":[83],"both":[84],"standard":[86],"buffer.":[92],"It":[93],"can":[94],"be":[95],"applied":[96],"with":[97,145],"or":[98],"without":[99],"techniques":[101],"hindsight":[103],"(HER)":[106],"prioritized":[108],"(PER).":[111],"Our":[112,153],"significantly":[114],"improves":[115],"state-of-the-art,":[120],"validated":[121],"8":[123],"tasks":[124],"three":[126],"robotic":[127],"benchmarks.":[128],"exploit":[131],"full":[133],"potential":[134],"HiER,":[136],"HiER+":[139],"which":[141],"HiER":[142],"enhanced":[144],"an":[146],"arbitrary":[147],"data":[148],"collection":[149],"curriculum":[150],"learning":[151],"method.":[152],"implementation,":[154],"qualitative":[156],"results,":[157],"video":[160],"presentation":[161],"available":[163],"project":[166],"site:":[167],"<uri":[168],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[169],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">http://www.danielhorvath.eu/hier/</uri>.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}