{"id":"https://openalex.org/W2766180905","doi":"https://doi.org/10.1007/s10015-017-0401-2","title":"Robustness of linearly solvable Markov games employing inaccurate dynamics model","display_name":"Robustness of linearly solvable Markov games employing inaccurate dynamics model","publication_year":2017,"publication_date":"2017-10-31","ids":{"openalex":"https://openalex.org/W2766180905","doi":"https://doi.org/10.1007/s10015-017-0401-2","mag":"2766180905"},"language":"en","primary_location":{"id":"doi:10.1007/s10015-017-0401-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10015-017-0401-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10015-017-0401-2.pdf","source":{"id":"https://openalex.org/S104439334","display_name":"Artificial Life and Robotics","issn_l":"1433-5298","issn":["1433-5298","1614-7456"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Life and Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10015-017-0401-2.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085840994","display_name":"Ken Kinjo","orcid":null},"institutions":[{"id":"https://openalex.org/I142637625","display_name":"Okinawa Institute of Science and Technology Graduate University","ror":"https://ror.org/02qg15b79","country_code":"JP","type":"education","lineage":["https://openalex.org/I142637625"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ken Kinjo","raw_affiliation_strings":["Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan"],"affiliations":[{"raw_affiliation_string":"Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan","institution_ids":["https://openalex.org/I142637625"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031054137","display_name":"Eiji Uchibe","orcid":"https://orcid.org/0000-0001-7908-0258"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Eiji Uchibe","raw_affiliation_strings":["ATR Computational Neuroscience Laboratories, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"ATR Computational Neuroscience Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004840638","display_name":"Kenji Doya","orcid":"https://orcid.org/0000-0002-2446-6820"},"institutions":[{"id":"https://openalex.org/I142637625","display_name":"Okinawa Institute of Science and Technology Graduate University","ror":"https://ror.org/02qg15b79","country_code":"JP","type":"education","lineage":["https://openalex.org/I142637625"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenji Doya","raw_affiliation_strings":["Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan"],"affiliations":[{"raw_affiliation_string":"Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan","institution_ids":["https://openalex.org/I142637625"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031054137"],"corresponding_institution_ids":["https://openalex.org/I4210104143"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.2079,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65457287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"23","issue":"1","first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9617000222206116,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9613000154495239,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/robustness","display_name":"Robustness (evolution)","score":0.784538984298706},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7775449156761169},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.690943717956543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6868996620178223},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5688883066177368},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5640581250190735},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.48177000880241394},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.4643104076385498},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.4531451165676117},{"id":"https://openalex.org/keywords/system-dynamics","display_name":"System dynamics","score":0.4333038926124573},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.41995781660079956},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.323575884103775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2981775403022766},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28447192907333374},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2331324815750122}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.784538984298706},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7775449156761169},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.690943717956543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6868996620178223},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5688883066177368},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5640581250190735},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.48177000880241394},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.4643104076385498},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4531451165676117},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.4333038926124573},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.41995781660079956},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.323575884103775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2981775403022766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28447192907333374},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2331324815750122},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10015-017-0401-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10015-017-0401-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10015-017-0401-2.pdf","source":{"id":"https://openalex.org/S104439334","display_name":"Artificial Life and Robotics","issn_l":"1433-5298","issn":["1433-5298","1614-7456"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Life and Robotics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10015-017-0401-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10015-017-0401-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10015-017-0401-2.pdf","source":{"id":"https://openalex.org/S104439334","display_name":"Artificial Life and Robotics","issn_l":"1433-5298","issn":["1433-5298","1614-7456"],"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Life and Robotics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3772331960","display_name":null,"funder_award_id":"17H06042","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2766180905.pdf","grobid_xml":"https://content.openalex.org/works/W2766180905.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1506276357","https://openalex.org/W1579118835","https://openalex.org/W2008920573","https://openalex.org/W2029722408","https://openalex.org/W2066920868","https://openalex.org/W2078639473","https://openalex.org/W2093524643","https://openalex.org/W2105078254","https://openalex.org/W2121863487","https://openalex.org/W2128152413","https://openalex.org/W2155919457","https://openalex.org/W2963298284","https://openalex.org/W4214717370","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4225269853"],"abstract_inverted_index":{"As":[0],"a":[1,100],"model-based":[2,35],"reinforcement":[3,36],"learning":[4],"technique,":[5],"linearly":[6,58],"solvable":[7,59],"Markov":[8,60],"decision":[9],"process":[10],"(LMDP)":[11],"gives":[12],"an":[13,18,68,143],"efficient":[14],"way":[15],"to":[16,44],"find":[17],"optimal":[19],"policy":[20,110,120,130],"by":[21],"making":[22],"the":[23,38,45,48,53,56,74,80,103,108,114,117,127,136,147],"Bellman":[24],"equation":[25],"linear":[26],"under":[27],"some":[28],"assumptions.":[29],"Since":[30],"LMDP":[31,41,71],"is":[32,42,67,99,149],"regarded":[33],"as":[34],"learning,":[37],"performance":[39,123],"of":[40,47,55,70,82,113,126,138,146],"sensitive":[43],"accuracy":[46],"environmental":[49],"model.":[50],"To":[51],"overcome":[52],"problem":[54],"sensitivity,":[57],"game":[61,75],"(LMG)":[62],"has":[63],"been":[64],"proposed,":[65],"which":[66],"extension":[69],"based":[72],"on":[73],"theory.":[76],"This":[77],"paper":[78],"investigates":[79],"robustness":[81],"LMDP-":[83],"and":[84,93,111],"LMG-based":[85,118],"controllers":[86],"against":[87],"modeling":[88],"errors":[89],"in":[90],"both":[91],"discrete":[92],"continuous":[94],"state-action":[95],"problems.":[96],"When":[97],"there":[98],"discrepancy":[101],"between":[102],"model":[104,145],"used":[105],"for":[106],"building":[107],"control":[109,119,129],"dynamics":[112],"tested":[115],"environment,":[116],"maintained":[121],"good":[122],"while":[124],"that":[125],"LMDP-based":[128],"deteriorated":[131],"drastically.":[132],"Experimental":[133],"results":[134],"support":[135],"usefulness":[137],"LMG":[139],"framework":[140],"when":[141],"acquiring":[142],"accurate":[144],"environment":[148],"difficult.":[150]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}