{"id":"https://openalex.org/W2897200624","doi":"https://doi.org/10.1109/ijcnn.2018.8489029","title":"Towards Designing Optimal Reward Functions in Multi-Agent Reinforcement Learning Problems","display_name":"Towards Designing Optimal Reward Functions in Multi-Agent Reinforcement Learning Problems","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2897200624","doi":"https://doi.org/10.1109/ijcnn.2018.8489029","mag":"2897200624"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2018.8489029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","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/A5027755211","display_name":"Ricardo Grunitzki","orcid":null},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Ricardo Grunitzki","raw_affiliation_strings":["Instituto de Inform\u00e1tica (INF) - Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, RS, Brasil"],"affiliations":[{"raw_affiliation_string":"Instituto de Inform\u00e1tica (INF) - Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, RS, Brasil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100634614","display_name":"Bruno C. da Silva","orcid":"https://orcid.org/0000-0002-6467-9943"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Bruno C. da Silva","raw_affiliation_strings":["Instituto de Inform\u00e1tica (INF) - Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, RS, Brasil"],"affiliations":[{"raw_affiliation_string":"Instituto de Inform\u00e1tica (INF) - Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, RS, Brasil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077312266","display_name":"L. C. Ana Bazzan","orcid":null},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"L. C. Ana Bazzan","raw_affiliation_strings":["Instituto de Inform\u00e1tica (INF) - Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, RS, Brasil"],"affiliations":[{"raw_affiliation_string":"Instituto de Inform\u00e1tica (INF) - Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, RS, Brasil","institution_ids":["https://openalex.org/I130442723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027755211"],"corresponding_institution_ids":["https://openalex.org/I130442723"],"apc_list":null,"apc_paid":null,"fwci":0.8144,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79976318,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9797999858856201,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.968999981880188,"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":0.9043653011322021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7035861015319824},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6132835745811462},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.578995943069458},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5343714356422424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4637850522994995},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.4140603244304657},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39499059319496155},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11214473843574524}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9043653011322021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7035861015319824},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6132835745811462},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.578995943069458},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5343714356422424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4637850522994995},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.4140603244304657},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39499059319496155},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11214473843574524},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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":1,"locations":[{"id":"doi:10.1109/ijcnn.2018.8489029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W206679605","https://openalex.org/W1486707268","https://openalex.org/W1525481342","https://openalex.org/W1777239053","https://openalex.org/W2014394432","https://openalex.org/W2025565923","https://openalex.org/W2031571562","https://openalex.org/W2099618002","https://openalex.org/W2121863487","https://openalex.org/W2123408238","https://openalex.org/W2160088187","https://openalex.org/W2163602945","https://openalex.org/W2164419340","https://openalex.org/W2164424353","https://openalex.org/W2495333748","https://openalex.org/W2544765807","https://openalex.org/W2556366151","https://openalex.org/W2592535843","https://openalex.org/W4214717370","https://openalex.org/W6628902087","https://openalex.org/W6631628264","https://openalex.org/W6638088447","https://openalex.org/W6683991275","https://openalex.org/W6684159546"],"related_works":["https://openalex.org/W2113265763","https://openalex.org/W4361804730","https://openalex.org/W2142113611","https://openalex.org/W2334467465","https://openalex.org/W2018387840","https://openalex.org/W2087870008","https://openalex.org/W2045629210","https://openalex.org/W2162534555","https://openalex.org/W2752178021","https://openalex.org/W2107419853"],"abstract_inverted_index":{"Defining":[0],"a":[1,9,105,163],"reward":[2,35,42,86,108,118,126,129,134,171,177,204],"function":[3],"that,":[4],"when":[5,24,83],"optimized,":[6],"results":[7,185],"in":[8,68,167,181,201],"rapid":[10],"acquisition":[11],"of":[12,18,52,75,157,170,176,198],"an":[13,97],"optimal":[14,34,98,117],"policy,":[15],"is":[16,47,137,150],"one":[17],"the":[19,33,76,85,115,133,168,174,196],"most":[20],"challenging":[21],"problems":[22,153],"involved":[23],"deploying":[25],"reinforcement":[26,56,146],"learning":[27,57,147,159,164],"algorithms.":[28],"The":[29],"existing":[30],"works":[31],"on":[32,186],"problem":[36,119],"(ORP)":[37],"propose":[38],"mechanisms":[39],"to":[40,49,140,152,194],"design":[41],"functions":[43,172,178],"but":[44,71],"their":[45],"application":[46],"limited":[48],"specific":[50],"sub-classes":[51],"single":[53,143],"or":[54,78],"multi-agent":[55,145],"problems.":[58],"Moreover,":[59],"these":[60],"methods":[61,89],"identify":[62,124],"which":[63,69,73],"rewards":[64],"should":[65,80],"be":[66,81,101],"given":[67,106],"situation,":[70],"not":[72,92],"aspects":[74],"state":[77],"environment":[79],"used":[82,193],"defining":[84],"function.":[87,109],"Those":[88],"also":[90],"do":[91],"directly":[93],"model":[94],"how":[95],"quickly":[96],"policy":[99],"can":[100,123],"learned":[102],"by":[103],"optimizing":[104],"candidate":[107],"In":[110],"this":[111],"paper,":[112],"we":[113],"define":[114],"extended":[116],"(EORP)":[120],"which:":[121],"i)":[122],"both":[125],"features":[127],"and":[128,144,188],"weights":[130],"that":[131,179],"compose":[132],"function;":[135],"ii)":[136],"general":[138],"enough":[139],"deal":[141],"with":[142,154],"problems;":[148],"iii)":[149],"scalable":[151],"large":[155],"number":[156],"agents":[158],"simultaneously;":[160],"iv)":[161],"incorporates":[162],"effort":[165],"metric":[166],"evaluation":[169],"allowing":[173],"discovery":[175],"result":[180],"faster":[182],"learning.":[183],"Experimental":[184],"gridworld-like":[187],"traffic":[189],"assignment":[190],"scenarios":[191],"are":[192],"evaluate":[195],"efficiency":[197],"our":[199],"approach":[200],"designing":[202],"effective":[203],"functions.":[205]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}