{"id":"https://openalex.org/W2787270134","doi":"https://doi.org/10.24963/ijcai.2018/37","title":"Balancing Two-Player Stochastic Games with Soft Q-Learning","display_name":"Balancing Two-Player Stochastic Games with Soft Q-Learning","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2787270134","doi":"https://doi.org/10.24963/ijcai.2018/37","mag":"2787270134"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/37","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/37","pdf_url":"https://www.ijcai.org/proceedings/2018/0037.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2018/0037.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026686188","display_name":"Jordi Grau-Moya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jordi Grau-Moya","raw_affiliation_strings":["Prowler.io"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Prowler.io","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005192247","display_name":"Felix Leibfried","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felix Leibfried","raw_affiliation_strings":["Prowler.io"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Prowler.io","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034334762","display_name":"Haitham Bou Ammar","orcid":"https://orcid.org/0000-0002-6083-6171"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haitham Bou-Ammar","raw_affiliation_strings":["Prowler.io"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Prowler.io","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0137,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81907903,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"268","last_page":"274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9817000031471252,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9747999906539917,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7803734540939331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6965258717536926},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.562923014163971},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.5095593929290771},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4934152662754059},{"id":"https://openalex.org/keywords/fictitious-play","display_name":"Fictitious play","score":0.4775886535644531},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.45482778549194336},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.45010894536972046},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4082663953304291},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.3520740866661072},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.3100287914276123},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15238052606582642},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08938875794410706}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7803734540939331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6965258717536926},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.562923014163971},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.5095593929290771},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4934152662754059},{"id":"https://openalex.org/C145071142","wikidata":"https://www.wikidata.org/wiki/Q1411116","display_name":"Fictitious play","level":3,"score":0.4775886535644531},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.45482778549194336},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.45010894536972046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4082663953304291},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.3520740866661072},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3100287914276123},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15238052606582642},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08938875794410706},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.24963/ijcai.2018/37","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/37","pdf_url":"https://www.ijcai.org/proceedings/2018/0037.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1802.03216","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.03216","pdf_url":"https://arxiv.org/pdf/1802.03216","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:2787270134","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1802.03216.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1802.03216","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1802.03216","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2018/37","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/37","pdf_url":"https://www.ijcai.org/proceedings/2018/0037.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2787270134.pdf","grobid_xml":"https://content.openalex.org/works/W2787270134.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1626977535","https://openalex.org/W1771410628","https://openalex.org/W1974246960","https://openalex.org/W2026659355","https://openalex.org/W2081484203","https://openalex.org/W2101692583","https://openalex.org/W2108703536","https://openalex.org/W2109100253","https://openalex.org/W2127775068","https://openalex.org/W2145339207","https://openalex.org/W2239029832","https://openalex.org/W2337698339","https://openalex.org/W2402108766","https://openalex.org/W2485180682","https://openalex.org/W2527782253","https://openalex.org/W2594103415","https://openalex.org/W2744355733","https://openalex.org/W2788807191","https://openalex.org/W2911283634","https://openalex.org/W2962950744","https://openalex.org/W2963373084","https://openalex.org/W2963817734","https://openalex.org/W6640388115","https://openalex.org/W6663231754"],"related_works":["https://openalex.org/W2963390138","https://openalex.org/W1790692380","https://openalex.org/W2014852613","https://openalex.org/W3138460475","https://openalex.org/W2951859429","https://openalex.org/W2188793289","https://openalex.org/W2618299181","https://openalex.org/W2905298280","https://openalex.org/W2993335844","https://openalex.org/W2949381094","https://openalex.org/W2999610183","https://openalex.org/W3185211981","https://openalex.org/W3208644168","https://openalex.org/W3085581910","https://openalex.org/W2996203124","https://openalex.org/W2730807149","https://openalex.org/W3169429640","https://openalex.org/W3118463161","https://openalex.org/W3138162409","https://openalex.org/W2972112708"],"abstract_inverted_index":{"Within":[0],"the":[1,6,73],"context":[2],"of":[3,8,104],"video":[4],"games":[5,32,79,90,93,127],"notion":[7],"perfectly":[9],"rational":[10],"agents":[11],"can":[12],"be":[13],"undesirable":[14],"as":[15,39],"it":[16],"leads":[17],"to":[18,56,99,124],"uninteresting":[19],"situations,":[20],"where":[21,59],"humans":[22],"face":[23],"tough":[24],"adversarial":[25],"decision":[26],"makers.":[27],"Current":[28],"frameworks":[29],"for":[30],"stochastic":[31,57],"and":[33,70,87,91,116],"reinforcement":[34],"learning":[35],"prohibit":[36],"tuneable":[37,50],"strategies":[38],"they":[40],"seek":[41],"optimal":[42],"performance.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47,76,108],"enable":[48],"such":[49],"behaviour":[51],"by":[52],"generalising":[53],"soft":[54,81],"Q-learning":[55,82],"games,":[58],"more":[60],"than":[61],"one":[62],"agent":[63],"interact":[64],"strategically.":[65],"We":[66],"contribute":[67],"both":[68],"theoretically":[69],"empirically.":[71],"On":[72],"theory":[74],"side,":[75],"show":[77,109],"that":[78],"with":[80,128],"exhibit":[83],"a":[84,101,119],"unique":[85],"value":[86],"generalise":[88],"team":[89],"zero-sum":[92],"far":[94],"beyond":[95],"these":[96],"two":[97],"extremes":[98],"cover":[100],"continuous":[102],"spectrum":[103],"gaming":[105],"behaviour.":[106],"Experimentally,":[107],"how":[110,123],"tuning":[111],"agents'":[112],"constraints":[113],"affect":[114],"performance":[115],"demonstrate,":[117],"through":[118],"neural":[120],"network":[121],"architecture,":[122],"reliably":[125],"balance":[126],"high-dimensional":[129],"representations.":[130]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}