{"id":"https://openalex.org/W1794865926","doi":"https://doi.org/10.1007/978-3-642-34799-3_10","title":"Multi-agent Learning and the Reinforcement Gradient","display_name":"Multi-agent Learning and the Reinforcement Gradient","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W1794865926","doi":"https://doi.org/10.1007/978-3-642-34799-3_10","mag":"1794865926"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-34799-3_10","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-34799-3_10","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5069752991","display_name":"Michael Kaisers","orcid":null},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Michael Kaisers","raw_affiliation_strings":["Departement of Knowledge Engineering, Maastricht University, Bouillonstraat 8-10, 6211, Maastricht, LH, The Netherlands","Department of Knowledge Engineering, Maastricht University, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Departement of Knowledge Engineering, Maastricht University, Bouillonstraat 8-10, 6211, Maastricht, LH, The Netherlands","institution_ids":["https://openalex.org/I34352273"]},{"raw_affiliation_string":"Department of Knowledge Engineering, Maastricht University, The Netherlands","institution_ids":["https://openalex.org/I34352273"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009474528","display_name":"Daan Bloembergen","orcid":"https://orcid.org/0000-0001-8200-9962"},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Daan Bloembergen","raw_affiliation_strings":["Department of Knowledge Engineering, Maastricht University, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Knowledge Engineering, Maastricht University, The Netherlands","institution_ids":["https://openalex.org/I34352273"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008547992","display_name":"Karl Tuyls","orcid":"https://orcid.org/0000-0001-7929-1944"},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Karl Tuyls","raw_affiliation_strings":["Department of Knowledge Engineering, Maastricht University, Bouillonstraat 8-10, 6211, Maastricht, LH, The Netherlands","Department of Knowledge Engineering, Maastricht University, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Knowledge Engineering, Maastricht University, Bouillonstraat 8-10, 6211, Maastricht, LH, The Netherlands","institution_ids":["https://openalex.org/I34352273"]},{"raw_affiliation_string":"Department of Knowledge Engineering, Maastricht University, The Netherlands","institution_ids":["https://openalex.org/I34352273"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069752991"],"corresponding_institution_ids":["https://openalex.org/I34352273"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16438002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"145","last_page":"159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"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":0.9976000189781189,"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/T11031","display_name":"Game Theory and Applications","score":0.9926999807357788,"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/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.989799976348877,"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":0.8637148141860962},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6844889521598816},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5926446914672852},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5497928857803345},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.5186976194381714},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43882983922958374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41503268480300903},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.39942336082458496},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27108433842658997},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20433184504508972},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19488921761512756}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8637148141860962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6844889521598816},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5926446914672852},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5497928857803345},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.5186976194381714},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43882983922958374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41503268480300903},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39942336082458496},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27108433842658997},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20433184504508972},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19488921761512756},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-642-34799-3_10","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-34799-3_10","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.722.745","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.722.745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.michaelkaisers.com/publications/2011_EUMAS_MKaisers.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1515851193","https://openalex.org/W1557517019","https://openalex.org/W1567092208","https://openalex.org/W1570317428","https://openalex.org/W1596771711","https://openalex.org/W1607392272","https://openalex.org/W1854866626","https://openalex.org/W1964199760","https://openalex.org/W1967829443","https://openalex.org/W1995622844","https://openalex.org/W2026069625","https://openalex.org/W2031098375","https://openalex.org/W2064018461","https://openalex.org/W2085728653","https://openalex.org/W2097160297","https://openalex.org/W2099618002","https://openalex.org/W2105643086","https://openalex.org/W2120327309","https://openalex.org/W2121863487","https://openalex.org/W2123890518","https://openalex.org/W2138914910","https://openalex.org/W2156194062","https://openalex.org/W2168913895","https://openalex.org/W2186731336","https://openalex.org/W2214788357","https://openalex.org/W3105048218","https://openalex.org/W3199187481","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2101991911","https://openalex.org/W2155070487","https://openalex.org/W4311589891","https://openalex.org/W1925875298","https://openalex.org/W4292701710"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}