{"id":"https://openalex.org/W2740459380","doi":"https://doi.org/10.24963/ijcai.2017/63","title":"Multi-Agent Planning with Baseline Regret Minimization","display_name":"Multi-Agent Planning with Baseline Regret Minimization","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2740459380","doi":"https://doi.org/10.24963/ijcai.2017/63","mag":"2740459380"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/63","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/63","pdf_url":"https://www.ijcai.org/proceedings/2017/0063.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0063.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029102289","display_name":"Feng Wu","orcid":"https://orcid.org/0000-0003-3989-0509"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Wu","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, CHN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, CHN","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027224308","display_name":"Shlomo Zilberstein","orcid":"https://orcid.org/0000-0001-9817-7848"},"institutions":[{"id":"https://openalex.org/I177605424","display_name":"Amherst College","ror":"https://ror.org/028vqfs63","country_code":"US","type":"education","lineage":["https://openalex.org/I177605424"]},{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shlomo Zilberstein","raw_affiliation_strings":["College of Information and Computer Sciences, University of Massachusetts Amherst","College of Information and Computer Sciences, University of Massachusetts Amherst, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information and Computer Sciences, University of Massachusetts Amherst","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"College of Information and Computer Sciences, University of Massachusetts Amherst, USA","institution_ids":["https://openalex.org/I177605424","https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084710341","display_name":"Xiaoping Chen","orcid":"https://orcid.org/0000-0001-8992-9286"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoping Chen","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, CHN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, CHN","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4131,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72032598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"444","last_page":"450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9948999881744385,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.9528825283050537},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.9456243515014648},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7746853828430176},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6581036448478699},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6366256475448608},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.6093128323554993},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.540120005607605},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4256395101547241},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24773284792900085},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21290376782417297},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17024070024490356}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9528825283050537},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.9456243515014648},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7746853828430176},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6581036448478699},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6366256475448608},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.6093128323554993},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.540120005607605},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4256395101547241},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24773284792900085},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21290376782417297},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17024070024490356},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2017/63","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/63","pdf_url":"https://www.ijcai.org/proceedings/2017/0063.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/63","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/63","pdf_url":"https://www.ijcai.org/proceedings/2017/0063.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3307191521","display_name":null,"funder_award_id":"61603368","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740459380.pdf","grobid_xml":"https://content.openalex.org/works/W2740459380.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W24098402","https://openalex.org/W85998123","https://openalex.org/W110618639","https://openalex.org/W156814138","https://openalex.org/W309675244","https://openalex.org/W1503287497","https://openalex.org/W1541317966","https://openalex.org/W1543886905","https://openalex.org/W1554448638","https://openalex.org/W1575232410","https://openalex.org/W1664816613","https://openalex.org/W1798373787","https://openalex.org/W1908253641","https://openalex.org/W1936503582","https://openalex.org/W2004391169","https://openalex.org/W2088956500","https://openalex.org/W2101450289","https://openalex.org/W2103315867","https://openalex.org/W2120518702","https://openalex.org/W2124951610","https://openalex.org/W2158082107","https://openalex.org/W2161534526","https://openalex.org/W2162735718","https://openalex.org/W2189505099","https://openalex.org/W2290803484","https://openalex.org/W2294192315","https://openalex.org/W2472245206","https://openalex.org/W2557456403","https://openalex.org/W2951198288","https://openalex.org/W2963836326"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2101991911","https://openalex.org/W2155070487","https://openalex.org/W4311589891","https://openalex.org/W3123835761","https://openalex.org/W118270247"],"abstract_inverted_index":{"We":[0,36],"propose":[1,38],"a":[2,21],"novel":[3],"baseline":[4,34,50,64],"regret":[5],"minimization":[6],"algorithm":[7,43],"for":[8],"multi-agent":[9],"planning":[10],"problems":[11,71],"modeled":[12],"as":[13],"finite-horizon":[14],"decentralized":[15],"POMDPs.":[16],"It":[17],"guarantees":[18],"to":[19,32,44,57,59,76],"produce":[20],"policy":[22,61],"that":[23],"is":[24],"provably":[25],"better":[26],"than":[27],"or":[28],"at":[29],"least":[30],"equivalent":[31],"the":[33,49,60,77],"policy.":[35],"also":[37],"an":[39],"iterative":[40],"belief":[41],"generation":[42],"effectively":[45],"and":[46],"efficiently":[47],"minimize":[48],"regret,":[51],"which":[52],"only":[53],"requires":[54],"necessary":[55],"iterations":[56],"converge":[58],"with":[62],"minimum":[63],"regret.":[65],"Experimental":[66],"results":[67],"on":[68],"common":[69],"benchmark":[70],"confirm":[72],"its":[73],"advantage":[74],"comparing":[75],"state-of-the-art":[78],"approaches.":[79]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}