{"id":"https://openalex.org/W2576551432","doi":"https://doi.org/10.1017/s0269888915000193","title":"Context-sensitive reward shaping for sparse interaction multi-agent systems","display_name":"Context-sensitive reward shaping for sparse interaction multi-agent systems","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2576551432","doi":"https://doi.org/10.1017/s0269888915000193","mag":"2576551432"},"language":"en","primary_location":{"id":"doi:10.1017/s0269888915000193","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0269888915000193","pdf_url":null,"source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-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/A5067801628","display_name":"Yann-Micha\u00ebl De Hauwere","orcid":null},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Yann-Micha\u00ebl de Hauwere","raw_affiliation_strings":["Computational Modeling Lab, Vrije Universiteit Brussel Pleinlaan 2, 1050 Brussels, Belgium e-mail:"],"affiliations":[{"raw_affiliation_string":"Computational Modeling Lab, Vrije Universiteit Brussel Pleinlaan 2, 1050 Brussels, Belgium e-mail:","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048451922","display_name":"Sam Devlin","orcid":"https://orcid.org/0000-0002-7769-3090"},"institutions":[{"id":"https://openalex.org/I52099693","display_name":"University of York","ror":"https://ror.org/04m01e293","country_code":"GB","type":"education","lineage":["https://openalex.org/I52099693"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sam Devlin","raw_affiliation_strings":["Department of Computer Science, University of York Heslington, York, YO10 5DD, UK e-mail:"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of York Heslington, York, YO10 5DD, UK e-mail:","institution_ids":["https://openalex.org/I52099693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009587907","display_name":"Daniel Kudenko\u22c6","orcid":"https://orcid.org/0000-0003-3359-3255"},"institutions":[{"id":"https://openalex.org/I52099693","display_name":"University of York","ror":"https://ror.org/04m01e293","country_code":"GB","type":"education","lineage":["https://openalex.org/I52099693"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniel Kudenko","raw_affiliation_strings":["Department of Computer Science, University of York Heslington, York, YO10 5DD, UK e-mail:"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of York Heslington, York, YO10 5DD, UK e-mail:","institution_ids":["https://openalex.org/I52099693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064553018","display_name":"Ann Now\u00e9","orcid":"https://orcid.org/0000-0001-6346-4564"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Ann Now\u00e9","raw_affiliation_strings":["Computational Modeling Lab, Vrije Universiteit Brussel Pleinlaan 2, 1050 Brussels, Belgium e-mail:"],"affiliations":[{"raw_affiliation_string":"Computational Modeling Lab, Vrije Universiteit Brussel Pleinlaan 2, 1050 Brussels, Belgium e-mail:","institution_ids":["https://openalex.org/I13469542"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5067801628"],"corresponding_institution_ids":["https://openalex.org/I13469542"],"apc_list":null,"apc_paid":null,"fwci":0.857,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8501528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"31","issue":"1","first_page":"59","last_page":"76"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9814000129699707,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9767000079154968,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7494416236877441},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7306392788887024},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6974897980690002},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.6457846760749817},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6222524642944336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45977577567100525},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.42895931005477905},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36417803168296814},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08186644315719604}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7494416236877441},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7306392788887024},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6974897980690002},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.6457846760749817},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6222524642944336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45977577567100525},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.42895931005477905},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36417803168296814},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08186644315719604},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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:10.1017/s0269888915000193","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0269888915000193","pdf_url":null,"source":{"id":"https://openalex.org/S137506714","display_name":"The Knowledge Engineering Review","issn_l":"0269-8889","issn":["0269-8889","1469-8005"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Knowledge Engineering Review","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7479391602","display_name":null,"funder_award_id":"EP/M023265/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W11035765","https://openalex.org/W119236796","https://openalex.org/W168445157","https://openalex.org/W1499408472","https://openalex.org/W1521003796","https://openalex.org/W1777239053","https://openalex.org/W2104602264","https://openalex.org/W2111316871","https://openalex.org/W2120846115","https://openalex.org/W2124152208","https://openalex.org/W2147750403","https://openalex.org/W2153427071","https://openalex.org/W2164637474","https://openalex.org/W2164851236","https://openalex.org/W2342543862","https://openalex.org/W2400387077","https://openalex.org/W2405266694","https://openalex.org/W2577085870","https://openalex.org/W3011120880","https://openalex.org/W4233696721","https://openalex.org/W6678168664"],"related_works":["https://openalex.org/W4388311650","https://openalex.org/W1974056099","https://openalex.org/W4306904969","https://openalex.org/W4245343541","https://openalex.org/W2386077341","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"Abstract":[0],"Potential-based":[1],"reward":[2,41,142],"shaping":[3,42,52,143],"is":[4],"a":[5,50,64,73,87,105,194,202],"commonly":[6],"used":[7,56,147],"approach":[8,192],"in":[9,20,47,60,72,86,90,116,130],"reinforcement":[10],"learning":[11,29],"to":[12,44,102,128,132,185],"direct":[13],"exploration":[14],"based":[15],"on":[16,148,193],"prior":[17],"knowledge.":[18],"Both":[19],"single":[21],"and":[22],"multi-agent":[23,48,88],"settings":[24],"this":[25],"technique":[26],"speeds":[27],"up":[28],"without":[30],"losing":[31],"any":[32],"theoretical":[33],"convergence":[34],"guarantees.":[35],"However,":[36],"if":[37],"speed":[38],"ups":[39],"through":[40],"are":[43,70,96],"be":[45,55,146,175,186],"achieved":[46],"environments,":[49],"different":[51,65,74,141],"signal":[53],"should":[54,163],"for":[57],"each":[58,165],"context":[59],"which":[61,91],"agents":[62,69,95,104,112,126,162],"have":[63],"subgoal":[66],"or":[67],"when":[68,161],"involved":[71],"interaction":[75],"situation.":[76],"This":[77,98],"paper":[78],"describes":[79],"the":[80,92,103,108,111,120,134,178,183],"use":[81],"of":[82,119,150,158,196,204],"context-aware":[83],"potential":[84],"functions":[85,144],"system":[89],"interactions":[93,109],"between":[94,110],"sparse.":[97],"means":[99],"that,":[100],"unknown":[101],"priori":[106],",":[107],"only":[113],"occur":[114],"sporadically":[115],"certain":[117],"regions":[118],"state":[121],"space.":[122],"During":[123],"these":[124],"interactions,":[125],"need":[127],"coordinate":[129],"order":[131],"reach":[133],"global":[135],"optimal":[136],"solution.":[137],"We":[138,189],"demonstrate":[139],"how":[140],"can":[145,173],"top":[149],"Future":[151],"Coordinating":[152],"Q-learning":[153],"(FCQ-learning);":[154],"an":[155],"algorithm":[156],"capable":[157],"automatically":[159],"detecting":[160],"take":[164],"other":[166],"into":[167],"consideration.":[168],"Using":[169],"FCQ-learning,":[170],"coordination":[171],"problems":[172,180,184],"even":[174],"anticipated":[176],"before":[177],"actual":[179],"occur,":[181],"allowing":[182],"solved":[187],"timely.":[188],"evaluate":[190],"our":[191],"range":[195],"gridworld":[197],"problems,":[198],"as":[199,201],"well":[200],"simulation":[203],"air":[205],"traffic":[206],"control.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-01-08T20:05:33.558190","created_date":"2025-10-10T00:00:00"}