{"id":"https://openalex.org/W3137629537","doi":"https://doi.org/10.1609/aaai.v35i8.16828","title":"Deep Radial-Basis Value Functions for Continuous Control","display_name":"Deep Radial-Basis Value Functions for Continuous Control","publication_year":2021,"publication_date":"2021-05-18","ids":{"openalex":"https://openalex.org/W3137629537","doi":"https://doi.org/10.1609/aaai.v35i8.16828","mag":"3137629537"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v35i8.16828","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v35i8.16828","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/16828/16635","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/16828/16635","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037667167","display_name":"Kavosh Asadi","orcid":null},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kavosh Asadi","raw_affiliation_strings":["Amazon Web Services, Brown University"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Brown University","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046930792","display_name":"Neev Parikh","orcid":null},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neev Parikh","raw_affiliation_strings":["Brown University"],"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109839104","display_name":"Ronald Parr","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ronald E. Parr","raw_affiliation_strings":["Duke University"],"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078124517","display_name":"George Konidaris","orcid":"https://orcid.org/0000-0002-4460-2519"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George D. Konidaris","raw_affiliation_strings":["Brown University"],"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009722403","display_name":"Michael L. Littman","orcid":"https://orcid.org/0000-0002-5596-1840"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Littman","raw_affiliation_strings":["Brown University"],"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5037667167"],"corresponding_institution_ids":["https://openalex.org/I27804330"],"apc_list":null,"apc_paid":null,"fwci":1.2566,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82650963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"35","issue":"8","first_page":"6696","last_page":"6704"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.991599977016449,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9811999797821045,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.7780009508132935},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6743918657302856},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.6727502942085266},{"id":"https://openalex.org/keywords/radial-basis-function","display_name":"Radial basis function","score":0.6706339716911316},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6233444213867188},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.5994283556938171},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5894260406494141},{"id":"https://openalex.org/keywords/basis-function","display_name":"Basis function","score":0.4827536940574646},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48240935802459717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47964292764663696},{"id":"https://openalex.org/keywords/radial-basis-function-network","display_name":"Radial basis function network","score":0.4641510248184204},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.4340288043022156},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.431530624628067},{"id":"https://openalex.org/keywords/continuous-function","display_name":"Continuous function (set theory)","score":0.42759883403778076},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.42142626643180847},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36418843269348145},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.323228657245636},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32297998666763306},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12452903389930725},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.07310488820075989}],"concepts":[{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.7780009508132935},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6743918657302856},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.6727502942085266},{"id":"https://openalex.org/C98856871","wikidata":"https://www.wikidata.org/wiki/Q1588488","display_name":"Radial basis function","level":3,"score":0.6706339716911316},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6233444213867188},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.5994283556938171},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5894260406494141},{"id":"https://openalex.org/C5917680","wikidata":"https://www.wikidata.org/wiki/Q2621825","display_name":"Basis function","level":2,"score":0.4827536940574646},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48240935802459717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47964292764663696},{"id":"https://openalex.org/C132917294","wikidata":"https://www.wikidata.org/wiki/Q2679684","display_name":"Radial basis function network","level":4,"score":0.4641510248184204},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4340288043022156},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.431530624628067},{"id":"https://openalex.org/C2778199601","wikidata":"https://www.wikidata.org/wiki/Q5165476","display_name":"Continuous function (set theory)","level":3,"score":0.42759883403778076},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42142626643180847},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36418843269348145},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.323228657245636},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32297998666763306},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12452903389930725},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.07310488820075989},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v35i8.16828","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v35i8.16828","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/16828/16635","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v35i8.16828","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v35i8.16828","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/16828/16635","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3137629537.pdf","grobid_xml":"https://content.openalex.org/works/W3137629537.grobid-xml"},"referenced_works_count":79,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W94523489","https://openalex.org/W164946830","https://openalex.org/W213063946","https://openalex.org/W1524100745","https://openalex.org/W1583833196","https://openalex.org/W1967005434","https://openalex.org/W1994833873","https://openalex.org/W2056653303","https://openalex.org/W2058755553","https://openalex.org/W2091565802","https://openalex.org/W2096053111","https://openalex.org/W2106261932","https://openalex.org/W2115519224","https://openalex.org/W2119567691","https://openalex.org/W2119821739","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2137983211","https://openalex.org/W2145339207","https://openalex.org/W2165150801","https://openalex.org/W2170141744","https://openalex.org/W2171277043","https://openalex.org/W2173248099","https://openalex.org/W2183243664","https://openalex.org/W2280163991","https://openalex.org/W2290354866","https://openalex.org/W2296319761","https://openalex.org/W2525954470","https://openalex.org/W2557283755","https://openalex.org/W2626384641","https://openalex.org/W2761873684","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2896412913","https://openalex.org/W2914921993","https://openalex.org/W2945159000","https://openalex.org/W2950471160","https://openalex.org/W2962902376","https://openalex.org/W2963169817","https://openalex.org/W2963266548","https://openalex.org/W2963864421","https://openalex.org/W2963910368","https://openalex.org/W2963923407","https://openalex.org/W2963938771","https://openalex.org/W2964158321","https://openalex.org/W2964291307","https://openalex.org/W2975587412","https://openalex.org/W2980603164","https://openalex.org/W2995801821","https://openalex.org/W3009498344","https://openalex.org/W3011120880","https://openalex.org/W3015662311","https://openalex.org/W3034442282","https://openalex.org/W3139377883","https://openalex.org/W3146803896","https://openalex.org/W4230914813","https://openalex.org/W4236579995","https://openalex.org/W4239510810","https://openalex.org/W4288614963","https://openalex.org/W4289372922","https://openalex.org/W4293871015","https://openalex.org/W4297814009","https://openalex.org/W4302570325","https://openalex.org/W6645264151","https://openalex.org/W6665018949","https://openalex.org/W6677313181","https://openalex.org/W6677916085","https://openalex.org/W6684205842","https://openalex.org/W6685951826","https://openalex.org/W6695011786","https://openalex.org/W6696324988","https://openalex.org/W6703110798","https://openalex.org/W6727685206","https://openalex.org/W6730267373","https://openalex.org/W6768034775","https://openalex.org/W6775686901","https://openalex.org/W6792155000","https://openalex.org/W6821113053"],"related_works":["https://openalex.org/W4230534566","https://openalex.org/W2105180757","https://openalex.org/W1992876914","https://openalex.org/W2184586959","https://openalex.org/W162769146","https://openalex.org/W2162304341","https://openalex.org/W1567195887","https://openalex.org/W157952102","https://openalex.org/W2471040861","https://openalex.org/W603561220"],"abstract_inverted_index":{"A":[0],"core":[1],"operation":[2,22],"in":[3],"reinforcement":[4],"learning":[5],"(RL)":[6],"is":[7,12,23,122],"finding":[8],"an":[9],"action":[10],"that":[11,59,111],"optimal":[13],"with":[14,50,63,105,124],"respect":[15,64],"to":[16,65,85,98],"a":[17,47,51,66,106],"learned":[18,28,45],"value":[19,29,40,43,82],"function.":[20],"This":[21],"often":[24],"challenging":[25],"when":[26],"the":[27,60,94,103,112],"function":[30,53,83,90],"takes":[31],"continuous":[32,99],"actions":[33],"as":[34],"input.":[35],"We":[36,57,92,109],"introduce":[37],"deep":[38,48,67,76,107],"radial-basis":[39,52],"functions":[41,44],"(RBVFs):":[42],"using":[46],"network":[49],"(RBF)":[54],"output":[55],"layer.":[56],"show":[58,110],"maximum":[61],"action-value":[62],"RBVF":[68],"can":[69,78],"be":[70],"approximated":[71],"easily":[72],"and":[73,121],"accurately.":[74],"Moreover,":[75],"RBVFs":[77],"represent":[79],"any":[80],"true":[81],"owing":[84],"their":[86],"support":[87],"for":[88],"universal":[89],"approximation.":[91],"extend":[93],"standard":[95],"DQN":[96],"algorithm":[97],"control":[100],"by":[101],"endowing":[102],"agent":[104],"RBVF.":[108],"resultant":[113],"agent,":[114],"called":[115],"RBF-DQN,":[116],"significantly":[117],"outperforms":[118],"value-function-only":[119],"baselines,":[120],"competitive":[123],"state-of-the-art":[125],"actor-critic":[126],"algorithms.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}