{"id":"https://openalex.org/W3200672436","doi":"https://doi.org/10.5220/0010762100003116","title":"Towards Multi-agent Reinforcement Learning using Quantum Boltzmann Machines","display_name":"Towards Multi-agent Reinforcement Learning using Quantum Boltzmann Machines","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3200672436","doi":"https://doi.org/10.5220/0010762100003116","mag":"3200672436"},"language":"en","primary_location":{"id":"doi:10.5220/0010762100003116","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010762100003116","pdf_url":null,"source":{"id":"https://openalex.org/S4363608837","display_name":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","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":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.5220/0010762100003116","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100653241","display_name":"Tobias M\u00fcller","orcid":"https://orcid.org/0000-0003-0013-8686"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Tobias M\u00fcller","raw_affiliation_strings":["Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023147780","display_name":"Christoph Roch","orcid":"https://orcid.org/0000-0003-0781-6590"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Roch","raw_affiliation_strings":["Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061867637","display_name":"Kyrill Schmid","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kyrill Schmid","raw_affiliation_strings":["Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065647323","display_name":"Philipp J. Altmann","orcid":"https://orcid.org/0000-0003-1134-176X"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Altmann","raw_affiliation_strings":["Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Mobile and Distributed Systems Group, LMU Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100653241"],"corresponding_institution_ids":["https://openalex.org/I8204097"],"apc_list":null,"apc_paid":null,"fwci":0.4158,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.54514113,"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":"121","last_page":"130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9983000159263611,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9983000159263611,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9976999759674072,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9962000250816345,"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":0.9291979074478149},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7451162934303284},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.5802026987075806},{"id":"https://openalex.org/keywords/restricted-boltzmann-machine","display_name":"Restricted Boltzmann machine","score":0.500438928604126},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.4853776693344116},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4732644855976105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47250139713287354},{"id":"https://openalex.org/keywords/quantum-machine-learning","display_name":"Quantum machine learning","score":0.4337036609649658},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34353527426719666},{"id":"https://openalex.org/keywords/quantum-computer","display_name":"Quantum computer","score":0.3266841173171997},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.22240394353866577},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16479969024658203}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9291979074478149},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7451162934303284},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.5802026987075806},{"id":"https://openalex.org/C199354608","wikidata":"https://www.wikidata.org/wiki/Q7316287","display_name":"Restricted Boltzmann machine","level":3,"score":0.500438928604126},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.4853776693344116},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4732644855976105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47250139713287354},{"id":"https://openalex.org/C2779094486","wikidata":"https://www.wikidata.org/wiki/Q18811578","display_name":"Quantum machine learning","level":4,"score":0.4337036609649658},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34353527426719666},{"id":"https://openalex.org/C58053490","wikidata":"https://www.wikidata.org/wiki/Q176555","display_name":"Quantum computer","level":3,"score":0.3266841173171997},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.22240394353866577},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16479969024658203},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0010762100003116","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010762100003116","pdf_url":null,"source":{"id":"https://openalex.org/S4363608837","display_name":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","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":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0010762100003116","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010762100003116","pdf_url":null,"source":{"id":"https://openalex.org/S4363608837","display_name":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","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":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1641379095","https://openalex.org/W1674280336","https://openalex.org/W1949466192","https://openalex.org/W1981783889","https://openalex.org/W1994630055","https://openalex.org/W2019013791","https://openalex.org/W2042492924","https://openalex.org/W2047057213","https://openalex.org/W2096698697","https://openalex.org/W2103956991","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2129670787","https://openalex.org/W2145339207","https://openalex.org/W2145805610","https://openalex.org/W2257979135","https://openalex.org/W2559394418","https://openalex.org/W2742896477","https://openalex.org/W2752862743","https://openalex.org/W2752947685","https://openalex.org/W2768956845","https://openalex.org/W2962938168","https://openalex.org/W2963000099","https://openalex.org/W2963531730","https://openalex.org/W3003533476","https://openalex.org/W3012922890","https://openalex.org/W3018195242","https://openalex.org/W3025817847","https://openalex.org/W3101987896","https://openalex.org/W3133137355","https://openalex.org/W3139377883"],"related_works":["https://openalex.org/W4283272532","https://openalex.org/W2952018105","https://openalex.org/W2119341610","https://openalex.org/W2916681395","https://openalex.org/W2556473569","https://openalex.org/W2193475944","https://openalex.org/W4302433642","https://openalex.org/W2529583158","https://openalex.org/W2108438604","https://openalex.org/W4394658668"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,12,24,50,115,154],"has":[2,30,45],"driven":[3],"impressive":[4],"advances":[5],"in":[6,51,82,126,141],"machine":[7,11],"learning.":[8],"Simultaneously,":[9],"quantum-enhanced":[10],"algorithms":[13],"using":[14],"quantum":[15],"annealing":[16],"underlie":[17],"heavy":[18],"developments.":[19],"Recently,":[20],"a":[21,149],"multi-agent":[22,68,142],"reinforcement":[23,49,153],"(MARL)":[25],"architecture":[26],"combining":[27],"both":[28],"paradigms":[29],"been":[31],"proposed.":[32],"This":[33],"novel":[34],"algorithm,":[35],"which":[36],"utilizes":[37],"Quantum":[38,144],"Boltzmann":[39,173],"Machines":[40],"(QBMs)":[41],"for":[42,103,152],"Q-value":[43],"approximation":[44],"outperformed":[46],"regular":[47],"deep":[48],"terms":[52],"of":[53,169],"time-steps":[54],"needed":[55],"to":[56,63,78,84,90,122,147],"converge.":[57],"However,":[58],"this":[59,72],"algorithm":[60],"was":[61],"restricted":[62],"single-agent":[64],"and":[65,99,107,119,164,172],"small":[66],"2x2":[67],"grid":[69],"domains.":[70,143],"In":[71],"work,":[73],"we":[74,93,132],"propose":[75],"an":[76,95],"extension":[77],"the":[79,105,138,161,167,170],"original":[80],"concept":[81],"order":[83],"solve":[85],"more":[86,117],"challenging":[87],"problems.":[88],"Similar":[89],"classic":[91],"DQNs,":[92],"add":[94],"experience":[96],"replay":[97],"buffer":[98],"use":[100],"different":[101],"networks":[102],"approximating":[104],"target":[106],"policy":[108],"values.":[109],"The":[110],"experimental":[111],"results":[112],"show":[113],"that":[114],"becomes":[116],"stable":[118],"enables":[120],"agents":[121,139],"find":[123],"optimal":[124],"policies":[125],"grid-domains":[127],"with":[128],"higher":[129],"complexity.":[130],"Additionally,":[131],"assess":[133],"how":[134],"parameter":[135],"sharing":[136],"influences":[137],"behavior":[140],"sampling":[145],"proves":[146],"be":[148],"promising":[150],"method":[151],"tasks,":[155],"but":[156],"is":[157],"currently":[158],"limited":[159],"by":[160,166],"QPU":[162],"size":[163,168],"therefore":[165],"input":[171],"machine.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}