{"id":"https://openalex.org/W2531648764","doi":"https://doi.org/10.1109/tcns.2016.2617622","title":"Model-Based Reinforcement Learning in Differential Graphical Games","display_name":"Model-Based Reinforcement Learning in Differential Graphical Games","publication_year":2016,"publication_date":"2016-10-13","ids":{"openalex":"https://openalex.org/W2531648764","doi":"https://doi.org/10.1109/tcns.2016.2617622","mag":"2531648764"},"language":"en","primary_location":{"id":"doi:10.1109/tcns.2016.2617622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcns.2016.2617622","pdf_url":null,"source":{"id":"https://openalex.org/S2502544478","display_name":"IEEE Transactions on Control of Network Systems","issn_l":"2325-5870","issn":["2325-5870","2372-2533"],"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 Control of Network Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1702.08584","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Rushikesh Kamalapurkar","orcid":"https://orcid.org/0000-0001-9963-5361"},"institutions":[{"id":"https://openalex.org/I115475287","display_name":"Oklahoma State University","ror":"https://ror.org/01g9vbr38","country_code":"US","type":"education","lineage":["https://openalex.org/I115475287"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rushikesh Kamalapurkar","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK, USA"],"raw_orcid":"https://orcid.org/0000-0001-9963-5361","affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Justin R. Klotz","orcid":"https://orcid.org/0000-0001-8393-7488"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin R. Klotz","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA"],"raw_orcid":"https://orcid.org/0000-0001-8393-7488","affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Patrick Walters","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Walters","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":null,"display_name":"Warren E. Dixon","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Warren E. Dixon","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9166,"has_fulltext":true,"cited_by_count":57,"citation_normalized_percentile":{"value":0.95472056,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"5","issue":"1","first_page":"423","last_page":"433"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9120000004768372,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9120000004768372,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.03799999877810478,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.020600000396370888,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7512999773025513},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.632099986076355},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.5533999800682068},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5501999855041504},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.535099983215332},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.47189998626708984},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4275999963283539},{"id":"https://openalex.org/keywords/differential-game","display_name":"Differential game","score":0.4097999930381775}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7512999773025513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6901999711990356},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.632099986076355},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.5533999800682068},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5501999855041504},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.47189998626708984},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4275999963283539},{"id":"https://openalex.org/C2779006483","wikidata":"https://www.wikidata.org/wiki/Q1973196","display_name":"Differential game","level":2,"score":0.4097999930381775},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3847000002861023},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.31839999556541443},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2939999997615814},{"id":"https://openalex.org/C91581856","wikidata":"https://www.wikidata.org/wiki/Q2707001","display_name":"Nonlinear control","level":3,"score":0.2890999913215637},{"id":"https://openalex.org/C192126672","wikidata":"https://www.wikidata.org/wiki/Q1068715","display_name":"Telecommunications network","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2825999855995178},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.26249998807907104}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcns.2016.2617622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcns.2016.2617622","pdf_url":null,"source":{"id":"https://openalex.org/S2502544478","display_name":"IEEE Transactions on Control of Network Systems","issn_l":"2325-5870","issn":["2325-5870","2372-2533"],"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 Control of Network Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1702.08584","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1702.08584","pdf_url":"https://arxiv.org/pdf/1702.08584","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1702.08584","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1702.08584","pdf_url":"https://arxiv.org/pdf/1702.08584","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4297280941","display_name":null,"funder_award_id":"N00014-13-1-0151","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4309261220","display_name":"Adaptive dynamic programming for uncertain nonlinear systems through coupling of nonlinear analysis and data-based learning","funder_award_id":"1509516","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5298401029","display_name":"NeTS: Small: Network Connectivity and Security for Cooperative Autonomous Vehicles","funder_award_id":"1217908","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5824843949","display_name":null,"funder_award_id":"N00014-16-1-2091","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2531648764.pdf","grobid_xml":"https://content.openalex.org/works/W2531648764.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1488435683","https://openalex.org/W1505754525","https://openalex.org/W1602326725","https://openalex.org/W1630241696","https://openalex.org/W1914756871","https://openalex.org/W1983523797","https://openalex.org/W1985349224","https://openalex.org/W1994203036","https://openalex.org/W1995638560","https://openalex.org/W1995661621","https://openalex.org/W1997603681","https://openalex.org/W2000995317","https://openalex.org/W2008588420","https://openalex.org/W2009303086","https://openalex.org/W2019338681","https://openalex.org/W2025421018","https://openalex.org/W2034114456","https://openalex.org/W2035608030","https://openalex.org/W2046888764","https://openalex.org/W2052369206","https://openalex.org/W2055300044","https://openalex.org/W2062697270","https://openalex.org/W2064347125","https://openalex.org/W2084063650","https://openalex.org/W2085194340","https://openalex.org/W2086975818","https://openalex.org/W2090284141","https://openalex.org/W2097253853","https://openalex.org/W2105014752","https://openalex.org/W2108383324","https://openalex.org/W2109606373","https://openalex.org/W2131363581","https://openalex.org/W2138131694","https://openalex.org/W2140665365","https://openalex.org/W2152047529","https://openalex.org/W2483203095","https://openalex.org/W2963093491","https://openalex.org/W2963609304","https://openalex.org/W3150098721","https://openalex.org/W4234761190","https://openalex.org/W4243848901","https://openalex.org/W4301747304","https://openalex.org/W6686464875"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"seeks":[2],"to":[3,12,60,67,79],"combine":[4],"differential":[5],"game":[6],"theory":[7],"with":[8],"the":[9,25,81,84],"actor-critic-identifier":[10],"architecture":[11],"determine":[13],"forward-in-time,":[14],"approximate":[15],"optimal":[16],"controllers":[17],"for":[18],"formation":[19],"tracking":[20],"in":[21,71],"multiagent":[22],"systems,":[23],"where":[24],"agents":[26,66],"have":[27],"uncertain":[28],"heterogeneous":[29],"nonlinear":[30],"dynamics.":[31],"A":[32,53],"continuous":[33],"control":[34,62],"strategy":[35],"is":[36,58],"proposed,":[37],"using":[38],"communication":[39,46],"feedback":[40],"from":[41],"extended":[42],"neighbors":[43],"on":[44],"a":[45,50,63,69,72],"topology":[47],"that":[48],"has":[49],"spanning":[51],"tree.":[52],"model-based":[54],"reinforcement":[55],"learning":[56],"technique":[57],"developed":[59,85],"cooperatively":[61],"group":[64],"of":[65,83],"track":[68],"trajectory":[70],"desired":[73],"formation.":[74],"Simulation":[75],"results":[76],"are":[77],"presented":[78],"demonstrate":[80],"performance":[82],"technique.":[86]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-10-21T00:00:00"}
