Estimation Monte Carlo sans modèle de politiques de décisionFonteneau, Raphaël ; ; Wehenkel, Louis et alin Revue d'Intelligence Artificielle [=RIA] (2011), 25 Detailed reference viewed: 9 (3 ULg) Apprentissage actif par modification de la politique de décision couranteFonteneau, Raphaël ; ; Wehenkel, Louis et alin Sixièmes Journées Francophones de Planification, Décision et Apprentissage pour la conduite de systèmes (JFPDA 2011) (2011, June) Detailed reference viewed: 9 (4 ULg) Computing bounds for kernel-based policy evaluation in reinforcement learningFonteneau, Raphaël ; ; Wehenkel, Louis et alReport (2010) This technical report proposes an approach for computing bounds on the finite-time return of a policy using kernel-based approximators from a sample of trajectories in a continuous state space and ... [more ▼] This technical report proposes an approach for computing bounds on the finite-time return of a policy using kernel-based approximators from a sample of trajectories in a continuous state space and deterministic framework. [less ▲] Detailed reference viewed: 9 (3 ULg) |
||