{"id":"https://openalex.org/W1485630385","doi":"https://doi.org/10.1007/3-540-45164-1_13","title":"Minimax TD-Learning with Neural Nets in a Markov Game","display_name":"Minimax TD-Learning with Neural Nets in a Markov Game","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W1485630385","doi":"https://doi.org/10.1007/3-540-45164-1_13","mag":"1485630385"},"language":"en","primary_location":{"id":"doi:10.1007/3-540-45164-1_13","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-45164-1_13","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/A5040631542","display_name":"Fredrik A. Dahl","orcid":"https://orcid.org/0000-0002-6835-0985"},"institutions":[{"id":"https://openalex.org/I163244428","display_name":"Norwegian Defence Research Establishment","ror":"https://ror.org/0098gnz32","country_code":"NO","type":"facility","lineage":["https://openalex.org/I163244428"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Fredrik A. Dahl","raw_affiliation_strings":["Norwegian Defence Research Establishment (FFI), Kjeller, Norway","Norwegian Defence Research Establishment (FFI) , Kjeller , Norway"],"affiliations":[{"raw_affiliation_string":"Norwegian Defence Research Establishment (FFI), Kjeller, Norway","institution_ids":["https://openalex.org/I163244428"]},{"raw_affiliation_string":"Norwegian Defence Research Establishment (FFI) , Kjeller , Norway","institution_ids":["https://openalex.org/I163244428"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070471012","display_name":"Ole Martin Halck","orcid":null},"institutions":[{"id":"https://openalex.org/I163244428","display_name":"Norwegian Defence Research Establishment","ror":"https://ror.org/0098gnz32","country_code":"NO","type":"facility","lineage":["https://openalex.org/I163244428"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Ole Martin Halck","raw_affiliation_strings":["Norwegian Defence Research Establishment (FFI), Kjeller, Norway","Norwegian Defence Research Establishment (FFI) , Kjeller , Norway"],"affiliations":[{"raw_affiliation_string":"Norwegian Defence Research Establishment (FFI), Kjeller, Norway","institution_ids":["https://openalex.org/I163244428"]},{"raw_affiliation_string":"Norwegian Defence Research Establishment (FFI) , Kjeller , Norway","institution_ids":["https://openalex.org/I163244428"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040631542"],"corresponding_institution_ids":["https://openalex.org/I163244428"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.1532,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75639406,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"117","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9972000122070312,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9732000231742859,"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/minimax","display_name":"Minimax","score":0.841861367225647},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7459492683410645},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5746188163757324},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.556010901927948},{"id":"https://openalex.org/keywords/zero-sum-game","display_name":"Zero-sum game","score":0.5489927530288696},{"id":"https://openalex.org/keywords/perfect-information","display_name":"Perfect information","score":0.5329500436782837},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.47980597615242004},{"id":"https://openalex.org/keywords/sequential-game","display_name":"Sequential game","score":0.47447922825813293},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.47065937519073486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4685301184654236},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.45365798473358154},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4518912434577942},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4366539418697357},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.426751971244812},{"id":"https://openalex.org/keywords/example-of-a-game-without-a-value","display_name":"Example of a game without a value","score":0.42215168476104736},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.38833847641944885},{"id":"https://openalex.org/keywords/normal-form-game","display_name":"Normal-form game","score":0.3424527645111084},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.30436912178993225},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.20627909898757935},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18417954444885254},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.07608082890510559}],"concepts":[{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.841861367225647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7459492683410645},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5746188163757324},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.556010901927948},{"id":"https://openalex.org/C136356330","wikidata":"https://www.wikidata.org/wiki/Q156612","display_name":"Zero-sum game","level":3,"score":0.5489927530288696},{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.5329500436782837},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.47980597615242004},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.47447922825813293},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.47065937519073486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4685301184654236},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.45365798473358154},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4518912434577942},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4366539418697357},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.426751971244812},{"id":"https://openalex.org/C138328387","wikidata":"https://www.wikidata.org/wiki/Q5419308","display_name":"Example of a game without a value","level":5,"score":0.42215168476104736},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.38833847641944885},{"id":"https://openalex.org/C155930848","wikidata":"https://www.wikidata.org/wiki/Q1069099","display_name":"Normal-form game","level":4,"score":0.3424527645111084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30436912178993225},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.20627909898757935},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18417954444885254},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.07608082890510559},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/3-540-45164-1_13","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-45164-1_13","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W20481216","https://openalex.org/W1542941925","https://openalex.org/W1583837637","https://openalex.org/W1846446801","https://openalex.org/W2008519844","https://openalex.org/W2009533501","https://openalex.org/W2083347533","https://openalex.org/W2089415692","https://openalex.org/W2100677568","https://openalex.org/W2103626435","https://openalex.org/W2166635296","https://openalex.org/W2170120409","https://openalex.org/W2496649228","https://openalex.org/W2796837256","https://openalex.org/W2947154587","https://openalex.org/W4206454995","https://openalex.org/W4285719527","https://openalex.org/W4317707897"],"related_works":["https://openalex.org/W2395347989","https://openalex.org/W2910530315","https://openalex.org/W3125878904","https://openalex.org/W1514842472","https://openalex.org/W1978317827","https://openalex.org/W2057383904","https://openalex.org/W3084233102","https://openalex.org/W2276575217","https://openalex.org/W1485630385","https://openalex.org/W160951409"],"abstract_inverted_index":null,"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}