.:. Consultation > Par auteur > Antos .:.

5 documents classés par : Date Titre Nom du premier auteur Type de documents Date de dépôt

Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path Antos A., Szepesvari C., Munos R. Machine Learning Journal (2008) 71:89-129 [hal-00830201 - version 1]

Fitted Q-iteration in continuous action-space MDPs Antos A., Munos R., Szepesvari C. Dans Neural Information Processing Systems (2007) [inria-00203359 - version 1]

Fitted Q-iteration in continuous action-space MDPs Antos A., Munos R., Szepesvari C. (2007) [inria-00185311 - version 2]

Value-Iteration Based Fitted Policy Iteration: Learning with a Single Trajectory Antos A., Szepesvari C., Munos R. Dans IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning (2007) 2007 [inria-00124833 - version 1]

Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path Antos A., Szepesvari C., Munos R. Dans Conference On Learning Theory (2006) [inria-00117130 - version 1]