Pub Date : 2011-09-09DOI: 10.1007/978-3-642-29946-9_5
Francis Maes, L. Wehenkel, D. Ernst
{"title":"Automatic Discovery of Ranking Formulas for Playing with Multi-armed Bandits","authors":"Francis Maes, L. Wehenkel, D. Ernst","doi":"10.1007/978-3-642-29946-9_5","DOIUrl":"https://doi.org/10.1007/978-3-642-29946-9_5","url":null,"abstract":"","PeriodicalId":432284,"journal":{"name":"European Workshop on Reinforcement Learning","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115146208","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-09-09DOI: 10.1007/978-3-642-29946-9_7
Matthew W. Robards, P. Sunehag
{"title":"Gradient Based Algorithms with Loss Functions and Kernels for Improved On-Policy Control","authors":"Matthew W. Robards, P. Sunehag","doi":"10.1007/978-3-642-29946-9_7","DOIUrl":"https://doi.org/10.1007/978-3-642-29946-9_7","url":null,"abstract":"","PeriodicalId":432284,"journal":{"name":"European Workshop on Reinforcement Learning","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128130351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-09-09DOI: 10.1007/978-3-642-29946-9_2
K. Kersting
{"title":"Invited Talk: Increasing Representational Power and Scaling Inference in Reinforcement Learning","authors":"K. Kersting","doi":"10.1007/978-3-642-29946-9_2","DOIUrl":"https://doi.org/10.1007/978-3-642-29946-9_2","url":null,"abstract":"","PeriodicalId":432284,"journal":{"name":"European Workshop on Reinforcement Learning","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121535827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-09-09DOI: 10.1007/978-3-642-29946-9_8
Mauricio Araya-López, O. Buffet, Vincent Thomas, F. Charpillet
{"title":"Active Learning of MDP Models","authors":"Mauricio Araya-López, O. Buffet, Vincent Thomas, F. Charpillet","doi":"10.1007/978-3-642-29946-9_8","DOIUrl":"https://doi.org/10.1007/978-3-642-29946-9_8","url":null,"abstract":"","PeriodicalId":432284,"journal":{"name":"European Workshop on Reinforcement Learning","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131919378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-09-09DOI: 10.1007/978-3-642-29946-9_25
G. Boutsioukis, Ioannis Partalas, I. Vlahavas
{"title":"Transfer Learning in Multi-Agent Reinforcement Learning Domains","authors":"G. Boutsioukis, Ioannis Partalas, I. Vlahavas","doi":"10.1007/978-3-642-29946-9_25","DOIUrl":"https://doi.org/10.1007/978-3-642-29946-9_25","url":null,"abstract":"","PeriodicalId":432284,"journal":{"name":"European Workshop on Reinforcement Learning","volume":"524 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123415986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-09-09DOI: 10.1007/978-3-642-29946-9_21
Cosmin Paduraru, Doina Precup, Joelle Pineau
{"title":"A Framework for Computing Bounds for the Return of a Policy","authors":"Cosmin Paduraru, Doina Precup, Joelle Pineau","doi":"10.1007/978-3-642-29946-9_21","DOIUrl":"https://doi.org/10.1007/978-3-642-29946-9_21","url":null,"abstract":"","PeriodicalId":432284,"journal":{"name":"European Workshop on Reinforcement Learning","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129749637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-09-09DOI: 10.1007/978-3-642-29946-9_15
Nikolaos Tziortziotis, K. Blekas
{"title":"Value Function Approximation through Sparse Bayesian Modeling","authors":"Nikolaos Tziortziotis, K. Blekas","doi":"10.1007/978-3-642-29946-9_15","DOIUrl":"https://doi.org/10.1007/978-3-642-29946-9_15","url":null,"abstract":"","PeriodicalId":432284,"journal":{"name":"European Workshop on Reinforcement Learning","volume":"225 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115492868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-09-09DOI: 10.1007/978-3-642-29946-9_32
K. Miyazaki, M. Ida
{"title":"Proposal and Evaluation of the Active Course Classification Support System with Exploitation-Oriented Learning","authors":"K. Miyazaki, M. Ida","doi":"10.1007/978-3-642-29946-9_32","DOIUrl":"https://doi.org/10.1007/978-3-642-29946-9_32","url":null,"abstract":"","PeriodicalId":432284,"journal":{"name":"European Workshop on Reinforcement Learning","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122760344","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2011-09-09DOI: 10.1007/978-3-642-29946-9_9
Boris Lesner, B. Zanuttini
{"title":"Handling Ambiguous Effects in Action Learning","authors":"Boris Lesner, B. Zanuttini","doi":"10.1007/978-3-642-29946-9_9","DOIUrl":"https://doi.org/10.1007/978-3-642-29946-9_9","url":null,"abstract":"","PeriodicalId":432284,"journal":{"name":"European Workshop on Reinforcement Learning","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127947258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：