{"id":"https://openalex.org/W2917442618","doi":"https://doi.org/10.4233/uuid:89c0f1a2-d19f-4466-9cc5-52aeb3950e53","title":"Resource-constrained Multi-agent Markov Decision Processes","display_name":"Resource-constrained Multi-agent Markov Decision Processes","publication_year":2019,"publication_date":"2019-02-22","ids":{"openalex":"https://openalex.org/W2917442618","doi":"https://doi.org/10.4233/uuid:89c0f1a2-d19f-4466-9cc5-52aeb3950e53","mag":"2917442618"},"language":"en","primary_location":{"id":"pmh:oai:tudelft.nl:uuid:89c0f1a2-d19f-4466-9cc5-52aeb3950e53","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:89c0f1a2-d19f-4466-9cc5-52aeb3950e53","pdf_url":"http://resolver.tudelft.nl/uuid:89c0f1a2-d19f-4466-9cc5-52aeb3950e53","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doctoral thesis"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://resolver.tudelft.nl/uuid:89c0f1a2-d19f-4466-9cc5-52aeb3950e53","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077292148","display_name":"Frits de Nijs","orcid":"https://orcid.org/0000-0003-4466-2447"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"F. de Nijs","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5077292148"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9801,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81552178,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6597999930381775,"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":0.6597999930381775,"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/T11810","display_name":"Complex Systems and Decision Making","score":0.6352999806404114,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.6133000254631042,"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":0.7594777345657349},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6855332851409912},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6560493111610413},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6039972901344299},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4780724048614502},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.464666485786438},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4641638398170471},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.41821327805519104},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4112669825553894},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3750356435775757},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3676639497280121},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3655984401702881}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7594777345657349},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6855332851409912},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6560493111610413},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6039972901344299},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4780724048614502},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.464666485786438},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4641638398170471},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.41821327805519104},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4112669825553894},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3750356435775757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3676639497280121},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3655984401702881},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:tudelft.nl:uuid:89c0f1a2-d19f-4466-9cc5-52aeb3950e53","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:89c0f1a2-d19f-4466-9cc5-52aeb3950e53","pdf_url":"http://resolver.tudelft.nl/uuid:89c0f1a2-d19f-4466-9cc5-52aeb3950e53","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doctoral thesis"},{"id":"doi:10.4233/uuid:89c0f1a2-d19f-4466-9cc5-52aeb3950e53","is_oa":true,"landing_page_url":"https://doi.org/10.4233/uuid:89c0f1a2-d19f-4466-9cc5-52aeb3950e53","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"thesis"},{"id":"mag:2917442618","is_oa":false,"landing_page_url":"https://repository.tudelft.nl/islandora/object/uuid%3A89c0f1a2-d19f-4466-9cc5-52aeb3950e53","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:tudelft.nl:uuid:89c0f1a2-d19f-4466-9cc5-52aeb3950e53","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:89c0f1a2-d19f-4466-9cc5-52aeb3950e53","pdf_url":"http://resolver.tudelft.nl/uuid:89c0f1a2-d19f-4466-9cc5-52aeb3950e53","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doctoral thesis"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2917442618.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2768425772","https://openalex.org/W2097127515","https://openalex.org/W3198981230","https://openalex.org/W1559517433","https://openalex.org/W2972298052","https://openalex.org/W3200635221","https://openalex.org/W3156869550","https://openalex.org/W2261683202","https://openalex.org/W2116916146","https://openalex.org/W2950530237","https://openalex.org/W2267132222","https://openalex.org/W2994642062","https://openalex.org/W2519695595","https://openalex.org/W2795190321","https://openalex.org/W2043081796","https://openalex.org/W2550308499","https://openalex.org/W1852310822","https://openalex.org/W130641071","https://openalex.org/W3132311446","https://openalex.org/W2951128282"],"abstract_inverted_index":{"Intelligent":[0],"autonomous":[1],"agents,":[2],"designed":[3],"to":[4,17,30,40,46,176,198],"automate":[5],"and":[6,144,157,179,217,242],"simplify":[7],"many":[8],"aspects":[9],"of":[10,51,65,80,94,111,127,133,163,202,250,274],"our":[11],"society,":[12],"will":[13],"increasingly":[14],"be":[15,261],"required":[16],"also":[18],"interact":[19],"with":[20,186],"other":[21],"agents":[22,25,36,66,73,235],"autonomously.":[23],"Where":[24],"interact,":[26],"they":[27],"are":[28,88,174,256],"likely":[29],"encounter":[31],"resource":[32,171,192,244],"constraints.":[33,228],"For":[34],"example,":[35],"managing":[37],"household":[38],"appliances":[39],"optimize":[41],"electricity":[42],"usage":[43],"might":[44],"need":[45],"share":[47],"the":[48,52,63,78,106,109,112,131,141,154,177,180,200,203,227,253,272],"limited":[49],"capacity":[50],"distribution":[53],"grid.<br/>This":[54],"thesis":[55],"describes":[56],"research":[57],"into":[58],"new":[59],"algorithms":[60,197,232],"for":[61,266],"optimizing":[62],"behavior":[64],"operating":[67],"in":[68,91,108,135,205,246],"constrained":[69,95],"environments,":[70],"when":[71,267],"these":[72,231],"have":[74],"significant":[75],"uncertainty":[76,107,241],"about":[77],"effects":[79],"their":[81,84,161,165,190,238],"actions":[82,113,239],"on":[83,140,153],"state.":[85],"Such":[86],"systems":[87],"effectively":[89],"modeled":[90],"a":[92,116,124,136,187,247,268],"framework":[93],"multi-agent":[96],"Markov":[97],"decision":[98],"processes":[99],"(MDPs).":[100],"A":[101],"single-agent":[102],"MDP":[103],"model":[104,126,220],"captures":[105],"outcome":[110],"chosen":[114,158],"by":[115,122],"specific":[117],"agent.":[118],"It":[119],"does":[120],"so":[121],"providing":[123],"probabilistic":[125],"state":[128,143,156,201],"transitions,":[129],"describing":[130],"likelihood":[132],"arriving":[134],"future":[137],"state,":[138],"conditional":[139],"current":[142,155],"action.":[145],"Agents":[146],"collect":[147],"different":[148],"rewards":[149],"or":[150],"penalties":[151],"depending":[152],"action,":[159],"informing":[160],"objective":[162,183],"maximizing":[164],"expected":[166],"reward.":[167],"To":[168],"include":[169],"constraints,":[170],"consumption":[172],"functions":[173],"added":[175],"actions,":[178],"agents'":[181],"(shared)":[182],"is":[184],"modified":[185],"condition":[188],"restricting":[189],"(cumulative)":[191],"consumption.":[193],"We":[194],"propose":[195],"novel":[196],"advance":[199],"art":[204],"three":[206],"challenging":[207],"settings:":[208],"computing":[209,213],"static":[210,258],"preallocations":[211,259],"off-line,":[212],"dynamic":[214,275],"(re)allocations":[215],"on-line,":[216],"optimally":[218],"learning":[219,225],"dynamics":[221],"through":[222],"safe":[223],"reinforcement":[224],"under":[226,240],"Taken":[229],"together,":[230],"show":[233],"how":[234],"can":[236,260],"coordinate":[237],"shared":[243],"constraints":[245],"broad":[248],"range":[249],"conditions.":[251],"Furthermore,":[252],"proposed":[254],"solutions":[255],"complementary:":[257],"used":[262],"as":[263],"back-up":[264],"strategy":[265],"communication":[269],"disruption":[270],"prevents":[271],"use":[273],"allocations.":[276]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}