{"id":"https://openalex.org/W3007998796","doi":"https://doi.org/10.1109/tnnls.2021.3103642","title":"Reinforcement Learning From Hierarchical Critics","display_name":"Reinforcement Learning From Hierarchical Critics","publication_year":2021,"publication_date":"2021-08-25","ids":{"openalex":"https://openalex.org/W3007998796","doi":"https://doi.org/10.1109/tnnls.2021.3103642","mag":"3007998796","pmid":"https://pubmed.ncbi.nlm.nih.gov/34432635"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3103642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3103642","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1902.03079","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007077356","display_name":"Zehong Cao","orcid":"https://orcid.org/0000-0003-3656-0328"},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zehong Cao","raw_affiliation_strings":["STEM, University of South Australia, Adelaide, SA, Australia","[STEM, University of South Australia, Adelaide, SA 5095, Australia (e-mail: zhcaonctu@gmail.com)]"],"raw_orcid":"https://orcid.org/0000-0003-3656-0328","affiliations":[{"raw_affiliation_string":"STEM, University of South Australia, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I170239107"]},{"raw_affiliation_string":"[STEM, University of South Australia, Adelaide, SA 5095, Australia (e-mail: zhcaonctu@gmail.com)]","institution_ids":["https://openalex.org/I170239107"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058936239","display_name":"Chin\u2010Teng Lin","orcid":"https://orcid.org/0000-0001-8371-8197"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chin-Teng Lin","raw_affiliation_strings":["School of Computer Science, Australian Artificial Intelligence Institute (AAII), University of Technology Sydney, Sydney, NSW, Australia","University of Technology, Sydney,"],"raw_orcid":"https://orcid.org/0000-0001-8371-8197","affiliations":[{"raw_affiliation_string":"School of Computer Science, Australian Artificial Intelligence Institute (AAII), University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"University of Technology, Sydney,","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5213,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71378015,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":"34","issue":"2","first_page":"1066","last_page":"1073"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.995199978351593,"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":0.995199978351593,"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/T11674","display_name":"Sports Analytics and Performance","score":0.9175000190734863,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9209194183349609},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.858385443687439},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.7692036628723145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.682011604309082},{"id":"https://openalex.org/keywords/competition","display_name":"Competition (biology)","score":0.6198673248291016},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6186301112174988},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5132948756217957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4779489040374756},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.44015198945999146},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33432793617248535},{"id":"https://openalex.org/keywords/management","display_name":"Management","score":0.13339358568191528},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11466491222381592},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08988261222839355},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.07565522193908691},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.06844624876976013}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9209194183349609},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.858385443687439},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.7692036628723145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.682011604309082},{"id":"https://openalex.org/C91306197","wikidata":"https://www.wikidata.org/wiki/Q45767","display_name":"Competition (biology)","level":2,"score":0.6198673248291016},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6186301112174988},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5132948756217957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4779489040374756},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.44015198945999146},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33432793617248535},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.13339358568191528},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11466491222381592},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08988261222839355},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.07565522193908691},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.06844624876976013},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/tnnls.2021.3103642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3103642","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:34432635","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34432635","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:arXiv.org:1902.03079","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.03079","pdf_url":"https://arxiv.org/pdf/1902.03079","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"","raw_type":"text"},{"id":"mag:3007998796","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1902.03079.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:figshare.com:article/22999427","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Reinforcement_learning_from_hierarchical_critics/22999427","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.48550/arxiv.1902.03079","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1902.03079","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1902.03079","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.03079","pdf_url":"https://arxiv.org/pdf/1902.03079","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1479148548","display_name":null,"funder_award_id":"ONRG-NICOP-N62909-19-1-2058","funder_id":"https://openalex.org/F4320338298","funder_display_name":"Office of Naval Research Global"},{"id":"https://openalex.org/G5816298421","display_name":"Cognitive intelligent information processing and presentation in navigation","funder_award_id":"DP180100656","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G7009114323","display_name":"Brain Robot Interface for Physical Human Robot Collaboration","funder_award_id":"DP210101093","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G7203342935","display_name":null,"funder_award_id":"ID10134","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"},{"id":"https://openalex.org/F4320338298","display_name":"Office of Naval Research Global","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3007998796.pdf","grobid_xml":"https://content.openalex.org/works/W3007998796.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W1973039793","https://openalex.org/W2056354534","https://openalex.org/W2107726111","https://openalex.org/W2134779831","https://openalex.org/W2145339207","https://openalex.org/W2154291838","https://openalex.org/W2173248099","https://openalex.org/W2274048525","https://openalex.org/W2335959470","https://openalex.org/W2523728418","https://openalex.org/W2594829461","https://openalex.org/W2617547828","https://openalex.org/W2736601468","https://openalex.org/W2765602917","https://openalex.org/W2889987506","https://openalex.org/W2913654295","https://openalex.org/W2950934634","https://openalex.org/W2962938168","https://openalex.org/W2963407617","https://openalex.org/W2963890729","https://openalex.org/W2964043796","https://openalex.org/W3093287223","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6734215269","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6749304979","https://openalex.org/W6752089545","https://openalex.org/W6753526802","https://openalex.org/W6757947852","https://openalex.org/W6758714175","https://openalex.org/W6759871227","https://openalex.org/W6763356705"],"related_works":["https://openalex.org/W2918312131","https://openalex.org/W2990628190","https://openalex.org/W2792745106","https://openalex.org/W2995726179","https://openalex.org/W2986409676","https://openalex.org/W2781726626","https://openalex.org/W1985680594","https://openalex.org/W3108562470","https://openalex.org/W2619219755","https://openalex.org/W2986185262","https://openalex.org/W3091147964","https://openalex.org/W3032032218","https://openalex.org/W3176265013","https://openalex.org/W2612795874","https://openalex.org/W3038835214","https://openalex.org/W3210590405","https://openalex.org/W3001141399","https://openalex.org/W2953334758","https://openalex.org/W3170059879","https://openalex.org/W2912646464"],"abstract_inverted_index":{"In":[0,55],"this":[1],"study,":[2],"we":[3,34,106],"investigate":[4],"the":[5,13,18,29,50,102,108,136,145],"use":[6],"of":[7,21,31,42,127],"global":[8,66,98],"information":[9,62,99],"to":[10,100],"speed":[11],"up":[12],"learning":[14,23],"process":[15],"and":[16,45,65,72,132],"increase":[17],"cumulative":[19],"rewards":[20],"reinforcement":[22],"(RL)":[24],"in":[25,77],"competition":[26,70],"tasks.":[27,151],"Within":[28],"framework":[30],"actor-critic":[32],"RL,":[33],"introduce":[35],"multiple":[36,74],"cooperative":[37,75],"critics":[38,52,67,76],"from":[39,49,63,93],"two":[40],"levels":[41],"a":[43,69,78,113],"hierarchy":[44],"propose":[46],"an":[47],"RL":[48],"hierarchical":[51],"(RLHC)":[53],"algorithm.":[54],"our":[56],"approach,":[57],"each":[58,82],"agent":[59,83],"receives":[60,86],"value":[61],"local":[64],"regarding":[68],"task":[71],"accesses":[73],"top-down":[79],"hierarchy.":[80],"Thus,":[81],"not":[84],"only":[85],"low-level":[87],"details,":[88],"but":[89],"also":[90],"considers":[91],"coordination":[92],"higher":[94],"levels,":[95],"thereby":[96],"obtaining":[97],"improve":[101],"training":[103],"performance.":[104],"Then,":[105],"test":[107],"proposed":[109],"RLHC":[110,143],"algorithm":[111],"against":[112],"benchmark":[114,146],"algorithm,":[115],"that":[116,142],"is,":[117],"proximal":[118],"policy":[119],"optimization":[120],"(PPO),":[121],"under":[122],"four":[123,149],"experimental":[124],"scenarios":[125],"consisting":[126],"tennis,":[128],"soccer,":[129],"banana":[130],"collection,":[131],"crawler":[133],"competitions":[134],"within":[135],"Unity":[137],"environment.":[138],"The":[139],"results":[140],"show":[141],"outperforms":[144],"on":[147],"these":[148],"competitive":[150]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}