Journal for General Philosophy of Science manuscript No. (will be inserted by the editor) Adaptive algorithms for meta-induction N.N. Received: date / Accepted: date Abstract Work in online…
Installationsanleitung für die Java JDK und den MUL Upload Client für Microsoft® Windows® Version: 2020-Q4 0. Prämissen Als Microsoft Windows Benutzer benötigen Sie hierfür mindestens Windows 8.1…
Linear Dependence of Stationary Distributions in Ergodic Markov Decision Processes Ronald Ortner Department Mathematik und Informationstechnologie, Montanuniversität Leoben Abstract In ergodic MDPs…
Improved Rates for the Stochastic Continuum-Armed Bandit Problem Peter Auer1 , Ronald Ortner1 , and Csaba Szepesvári2 1 University of Leoben, A-8700 Leoben, Austria auer@unileoben.ac.at,…
Pseudometrics for State Aggregation in Average Reward Markov Decision Processes Ronald Ortner University of Leoben, A-8700 Leoben, Austria ronald.ortner@unileoben.ac.at Abstract. We consider how…
Online Regret Bounds for Markov Decision Processes with Deterministic Transitions Ronald Ortner University of Leoben, A-8700 Leoben, Austria ronald.ortner@unileoben.ac.at Abstract. We consider an…
Optimism in the Face of Uncertainty Should be Refutable Ronald ORTNER Montanuniversität Leoben Department Mathematik und Informationstechnolgie Franz-Josef-Strasse 18, 8700 Leoben, Austria, Phone…
Online Regret Bounds for Markov Decision Processes with Deterministic TransitionsI Ronald Ortner Department Mathematik und Informationstechnologie, Montanuniversität Leoben, A-8700 Leoben, Austria …
EXPLOITING SIMILARITY INFORMATION IN REINFORCEMENT LEARNING Similarity Models for Multi-Armed Bandits and MDPs Ronald Ortner Lehrstuhl für Informationstechnologie, Montanuniversität Leoben…
