{"id":"https://openalex.org/W2973843138","doi":"https://doi.org/10.1109/coase.2019.8843223","title":"Constructive Policy: Reinforcement Learning Approach for Connected Multi-Agent Systems","display_name":"Constructive Policy: Reinforcement Learning Approach for Connected Multi-Agent Systems","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2973843138","doi":"https://doi.org/10.1109/coase.2019.8843223","mag":"2973843138"},"language":"en","primary_location":{"id":"doi:10.1109/coase.2019.8843223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coase.2019.8843223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5048669336","display_name":"Sayyed Jaffar Ali Raza","orcid":"https://orcid.org/0000-0002-0948-8263"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sayyed Jaffar Ali Raza","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060908808","display_name":"Mingjie Lin","orcid":"https://orcid.org/0000-0002-3225-4406"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingjie Lin","raw_affiliation_strings":["Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":null,"apc_paid":null,"fwci":0.6561,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75324326,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"17","issue":null,"first_page":"257","last_page":"262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9803000092506409,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9690999984741211,"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":0.8882774114608765},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7377453446388245},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5289058089256287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.501227855682373},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.456769198179245},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4509741961956024},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.4497253894805908},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4407746195793152},{"id":"https://openalex.org/keywords/constructive","display_name":"Constructive","score":0.4301181435585022},{"id":"https://openalex.org/keywords/local-search","display_name":"Local search (optimization)","score":0.42515069246292114},{"id":"https://openalex.org/keywords/local-optimum","display_name":"Local optimum","score":0.41167619824409485},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.08166411519050598}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8882774114608765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7377453446388245},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5289058089256287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.501227855682373},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.456769198179245},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4509741961956024},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4497253894805908},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4407746195793152},{"id":"https://openalex.org/C2778701210","wikidata":"https://www.wikidata.org/wiki/Q28130034","display_name":"Constructive","level":3,"score":0.4301181435585022},{"id":"https://openalex.org/C135320971","wikidata":"https://www.wikidata.org/wiki/Q1868524","display_name":"Local search (optimization)","level":2,"score":0.42515069246292114},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.41167619824409485},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.08166411519050598},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/coase.2019.8843223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coase.2019.8843223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1539216098","https://openalex.org/W1601081659","https://openalex.org/W1738827650","https://openalex.org/W1911551976","https://openalex.org/W1963649406","https://openalex.org/W2042882799","https://openalex.org/W2046376809","https://openalex.org/W2090170171","https://openalex.org/W2099201756","https://openalex.org/W2104733512","https://openalex.org/W2105947986","https://openalex.org/W2109910161","https://openalex.org/W2112361218","https://openalex.org/W2116611063","https://openalex.org/W2118318536","https://openalex.org/W2121863487","https://openalex.org/W2123967136","https://openalex.org/W2126880773","https://openalex.org/W2139612737","https://openalex.org/W2145339207","https://openalex.org/W2147667317","https://openalex.org/W2155007355","https://openalex.org/W2155027007","https://openalex.org/W2165150801","https://openalex.org/W2174364281","https://openalex.org/W2257979135","https://openalex.org/W2400458653","https://openalex.org/W2487144912","https://openalex.org/W2594103415","https://openalex.org/W2604726708","https://openalex.org/W2606433045","https://openalex.org/W2736601468","https://openalex.org/W2788148018","https://openalex.org/W2902143777","https://openalex.org/W2945728547","https://openalex.org/W2949186496","https://openalex.org/W2949561945","https://openalex.org/W2963161674","https://openalex.org/W2963262099","https://openalex.org/W2963403593","https://openalex.org/W2963864421","https://openalex.org/W2964161785","https://openalex.org/W2964262254","https://openalex.org/W4285719527","https://openalex.org/W4297669644","https://openalex.org/W4301422153","https://openalex.org/W4302570325","https://openalex.org/W6639904974","https://openalex.org/W6675200109","https://openalex.org/W6675977238","https://openalex.org/W6675999342","https://openalex.org/W6677834374","https://openalex.org/W6678157427","https://openalex.org/W6682849425","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6685200760","https://openalex.org/W6703271639","https://openalex.org/W6730038592","https://openalex.org/W6734517396","https://openalex.org/W6736368053","https://openalex.org/W6736742618","https://openalex.org/W6741002519","https://openalex.org/W6744935223","https://openalex.org/W6748702788","https://openalex.org/W6756714161"],"related_works":["https://openalex.org/W2123829500","https://openalex.org/W2305572622","https://openalex.org/W4283765137","https://openalex.org/W4317496694","https://openalex.org/W3174749984","https://openalex.org/W3208659968","https://openalex.org/W2887485518","https://openalex.org/W1655912143","https://openalex.org/W2560221187","https://openalex.org/W4286891850"],"abstract_inverted_index":{"Policy":[0],"based":[1,223],"reinforcement":[2],"learning":[3,70,96,134,194,199,244,277,285],"methods":[4,278],"are":[5,173],"widely":[6],"used":[7],"for":[8,138,206,265,287],"multi-agent":[9,26],"systems":[10,27],"to":[11,52,142,165,182,237,256,274],"learn":[12],"optimal":[13,225,267],"actions":[14],"given":[15],"any":[16],"state;":[17],"with":[18,28,35,133,259],"partial":[19],"or":[20,34,42],"even":[21],"no":[22,58],"model":[23,61,81],"representation.":[24,62],"However":[25],"complex":[29,288],"structures":[30],"(curse":[31],"of":[32,55,78,100,127,169,179,190,224,230,239,243,262],"dimensionality)":[33],"high":[36],"constraints":[37],"(like":[38],"bio-inspired":[39],"(a)":[40],"snake":[41],"serpentine":[43,257],"robots)":[44],"show":[45],"limited":[46],"performance":[47],"in":[48,98],"such":[49],"environments":[50],"due":[51,236],"sparse-reward":[53],"nature":[54],"environment":[56],"and":[57,71,88,93,102,117,197,210,241,269],"fully":[59],"observable":[60],"In":[63],"this":[64],"paper":[65],"we":[66,270],"present":[67],"a":[68,118,139,144,163],"constructive":[69,253],"planning":[72],"scheme":[73],"that":[74,123,147,172],"reduces":[75],"the":[76,111,184,202,252],"complexity":[77],"high-diemensional":[79],"agent":[80,141],"by":[82,154,187],"decomposing":[83],"it":[84],"into":[85,114],"identical,":[86],"connected":[87,177],"scaled":[89],"down":[90],"multiagent":[91],"structure":[92,178],"then":[94],"apply":[95,166,251],"framework":[97,203,286],"layers":[99],"local":[101,128,136,140,148,157,170,180,191,195,208,212],"global":[103,119,160,185,200,221],"ranking.":[104],"Our":[105],"layered":[106,284],"hierarchy":[107],"method":[108,255],"also":[109,151,271],"decomposes":[110],"final":[112],"goal":[113],"multiple":[115],"sub-tasks":[116,205,226],"task":[120,186],"(final":[121],"goal)":[122],"is":[124],"bias-induced":[125],"function":[126],"sub-tasks.":[129],"Local":[130],"layer":[131,161],"deals":[132],"`reusable'":[135],"policy":[137,149,164,254],"achieve":[143,183],"sub-task":[145],"optimally;":[146],"can":[150,280],"be":[152,281],"reused":[153],"other":[155],"identical":[156],"agents.":[158,192],"Furthermore,":[159],"learns":[162],"right":[167],"combination":[168],"policies":[171,196],"parameterized":[174],"over":[175,246],"entire":[176],"agents":[181],"collaborative":[188],"construction":[189],"After":[193],"while":[198],"policy,":[201],"generates":[204],"each":[207],"agent,":[209],"accepts":[211],"agents'":[213],"intrinsic":[214],"rewards":[215],"as":[216,283],"positive":[217],"bias":[218],"towards":[219],"maximum":[220],"reward":[222],"assignments.":[227],"The":[228],"advantage":[229],"proposed":[231],"approach":[232],"includes":[233],"better":[234],"exploration":[235],"decomposition":[238],"dimensions,":[240],"reusability":[242],"paradigm":[245],"extended":[247],"dimension":[248],"spaces.":[249],"We":[250],"robot":[258],"hyper-redundant":[260],"degrees":[261],"freedom":[263],"(DOF),":[264],"achieving":[266],"control":[268,289],"outline":[272],"connection":[273],"hierarchical":[275],"apprenticeship":[276],"which":[279],"seen":[282],"tasks.":[290]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}