{"id":"https://openalex.org/W3179226506","doi":"https://doi.org/10.1109/access.2021.3094623","title":"Contextual Bandit Learning With Reward Oracles and Sampling Guidance in Multi-Agent Environments","display_name":"Contextual Bandit Learning With Reward Oracles and Sampling Guidance in Multi-Agent Environments","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3179226506","doi":"https://doi.org/10.1109/access.2021.3094623","mag":"3179226506"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3094623","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3094623","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09474507.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09474507.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052977775","display_name":"Mike Li","orcid":"https://orcid.org/0000-0003-4514-7260"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mike Li","raw_affiliation_strings":["Centre for Complex Systems, Faculty of Engineering, University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-4514-7260","affiliations":[{"raw_affiliation_string":"Centre for Complex Systems, Faculty of Engineering, University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025929836","display_name":"Quang Dang Nguyen","orcid":"https://orcid.org/0000-0002-0403-6903"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Quang Dang Nguyen","raw_affiliation_strings":["Centre for Complex Systems, Faculty of Engineering, University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0403-6903","affiliations":[{"raw_affiliation_string":"Centre for Complex Systems, Faculty of Engineering, University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.2798,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63387707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"9","issue":null,"first_page":"96641","last_page":"96657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9980000257492065,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.7923058271408081},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7131269574165344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.67913818359375},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.573728084564209},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5668687224388123},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.5475923418998718},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5256420373916626},{"id":"https://openalex.org/keywords/offensive","display_name":"Offensive","score":0.5174587368965149},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.5054018497467041},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4941153824329376},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.47158730030059814},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4647449851036072},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4164494276046753},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.1294310986995697},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09343761205673218},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09130421280860901},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08529666066169739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7923058271408081},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7131269574165344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.67913818359375},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.573728084564209},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5668687224388123},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.5475923418998718},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5256420373916626},{"id":"https://openalex.org/C176856949","wikidata":"https://www.wikidata.org/wiki/Q2001676","display_name":"Offensive","level":2,"score":0.5174587368965149},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.5054018497467041},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4941153824329376},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.47158730030059814},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4647449851036072},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4164494276046753},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.1294310986995697},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09343761205673218},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09130421280860901},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08529666066169739},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3094623","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3094623","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09474507.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:fcb5205821ea46c889fa20c5bc1b4e47","is_oa":true,"landing_page_url":"https://doaj.org/article/fcb5205821ea46c889fa20c5bc1b4e47","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 96641-96657 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3094623","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3094623","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09474507.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320966","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3179226506.pdf","grobid_xml":"https://content.openalex.org/works/W3179226506.grobid-xml"},"referenced_works_count":118,"referenced_works":["https://openalex.org/W121645403","https://openalex.org/W1484799132","https://openalex.org/W1485123206","https://openalex.org/W1493210243","https://openalex.org/W1495978126","https://openalex.org/W1511887321","https://openalex.org/W1513468570","https://openalex.org/W1522301498","https://openalex.org/W1641379095","https://openalex.org/W1741816146","https://openalex.org/W1807600159","https://openalex.org/W1830835471","https://openalex.org/W1836465849","https://openalex.org/W1916369423","https://openalex.org/W1921016406","https://openalex.org/W1931877416","https://openalex.org/W1976115983","https://openalex.org/W1992935239","https://openalex.org/W2006410374","https://openalex.org/W2034587361","https://openalex.org/W2053767219","https://openalex.org/W2064380970","https://openalex.org/W2088956500","https://openalex.org/W2095705004","https://openalex.org/W2096145798","https://openalex.org/W2099618002","https://openalex.org/W2102222436","https://openalex.org/W2104602264","https://openalex.org/W2107280071","https://openalex.org/W2120591602","https://openalex.org/W2122097156","https://openalex.org/W2133552775","https://openalex.org/W2142839172","https://openalex.org/W2145339207","https://openalex.org/W2156662806","https://openalex.org/W2156876426","https://openalex.org/W2185472466","https://openalex.org/W2201581102","https://openalex.org/W2238973924","https://openalex.org/W2253157232","https://openalex.org/W2397581010","https://openalex.org/W2415726935","https://openalex.org/W2560622419","https://openalex.org/W2564749174","https://openalex.org/W2592798481","https://openalex.org/W2611191801","https://openalex.org/W2624784204","https://openalex.org/W2736601468","https://openalex.org/W2778588597","https://openalex.org/W2781726626","https://openalex.org/W2786928559","https://openalex.org/W2788862220","https://openalex.org/W2891663723","https://openalex.org/W2892283076","https://openalex.org/W2912998451","https://openalex.org/W2915454777","https://openalex.org/W2945073974","https://openalex.org/W2962804563","https://openalex.org/W2962957031","https://openalex.org/W2963376229","https://openalex.org/W2963406736","https://openalex.org/W2963477884","https://openalex.org/W2963864421","https://openalex.org/W2963933682","https://openalex.org/W2964121744","https://openalex.org/W2964278893","https://openalex.org/W2964896545","https://openalex.org/W2987257840","https://openalex.org/W2993541023","https://openalex.org/W2995676584","https://openalex.org/W2998377402","https://openalex.org/W2998579994","https://openalex.org/W2999146029","https://openalex.org/W3009211770","https://openalex.org/W3013697446","https://openalex.org/W3041510421","https://openalex.org/W3087279505","https://openalex.org/W3097731257","https://openalex.org/W3098133185","https://openalex.org/W3125733173","https://openalex.org/W4249725260","https://openalex.org/W4285719527","https://openalex.org/W4293583657","https://openalex.org/W4294635920","https://openalex.org/W4306179383","https://openalex.org/W6604960806","https://openalex.org/W6629456456","https://openalex.org/W6630520071","https://openalex.org/W6631190155","https://openalex.org/W6638375130","https://openalex.org/W6638667902","https://openalex.org/W6640174482","https://openalex.org/W6674330103","https://openalex.org/W6675811377","https://openalex.org/W6679184768","https://openalex.org/W6679700999","https://openalex.org/W6681246212","https://openalex.org/W6683161558","https://openalex.org/W6686298197","https://openalex.org/W6687681856","https://openalex.org/W6689974322","https://openalex.org/W6691230391","https://openalex.org/W6712392314","https://openalex.org/W6716193690","https://openalex.org/W6718147285","https://openalex.org/W6734678876","https://openalex.org/W6737185339","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748554570","https://openalex.org/W6748645729","https://openalex.org/W6748965644","https://openalex.org/W6749892895","https://openalex.org/W6754700182","https://openalex.org/W6754964036","https://openalex.org/W6758779491","https://openalex.org/W6771461125","https://openalex.org/W6846392434"],"related_works":["https://openalex.org/W2994202640","https://openalex.org/W272387213","https://openalex.org/W3108220207","https://openalex.org/W4287590860","https://openalex.org/W3120863400","https://openalex.org/W2955689724","https://openalex.org/W2981396729","https://openalex.org/W2990027495","https://openalex.org/W4319083788","https://openalex.org/W2747402019"],"abstract_inverted_index":{"Learning":[0],"action":[1,121],"policy":[2,122],"for":[3],"autonomous":[4],"agents":[5],"in":[6,25,34,118,123],"a":[7,26,42,66,85,132,139],"decentralized":[8],"multi-agent":[9],"environment":[10,130],"has":[11],"remained":[12],"an":[13,36,50,75],"interesting":[14],"but":[15],"difficult":[16],"research":[17],"problem.":[18],"We":[19],"propose":[20],"to":[21,55,82,84,138],"model":[22,57],"this":[23],"problem":[24],"contextual":[27],"bandit":[28],"setting":[29],"with":[30,52,92,100],"delayed":[31,59],"reward":[32,39,45,53,60,102],"signals,":[33],"particular":[35],"individual":[37],"short-term":[38],"signal":[40],"and":[41,62,98],"shared":[43],"long-term":[44],"signal.":[46],"Our":[47],"algorithm":[48,79,117],"utilizes":[49],"approach":[51],"oracles":[54],"directly":[56],"these":[58],"signals":[61],"also":[63],"relies":[64],"on":[65,94],"learning":[67,109,119],"scheme":[68],"benefiting":[69],"from":[70],"the":[71,112,115,124],"sampling":[72],"guidance":[73],"of":[74,88,114],"expert-designed":[76],"policy.":[77,141],"This":[78],"is":[80],"expected":[81],"apply":[83],"wide":[86],"range":[87],"problems,":[89],"including":[90],"those":[91,99],"constraints":[93],"accessing":[95],"state":[96],"transitions":[97],"implicit":[101],"information.":[103],"A":[104],"demonstration,":[105],"deployed":[106],"by":[107],"deep":[108],"regressors,":[110],"shows":[111],"effectiveness":[113],"proposed":[116],"offensive":[120],"RoboCup":[125],"Soccer":[126],"2D":[127],"Simulation":[128],"(RCSS)":[129],"against":[131],"well-known":[133],"adversary":[134],"benchmark":[135],"team":[136],"compared":[137],"baseline":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}