Jean Tarbouriech

sample complexity (5) markov decision process (5) reinforcement learning (4) stochastic shortest path (3) optimal policy (2) goal-conditioned policy (2) policy learning (1) pac learning (1) probabilistic inference (1) value iteration (1) model-based reinforcement learning (1) arm selection (1) linear function approximation (1) regret minimization (1) thompson sampling (1) autonomous exploration (1) pac bound (1) posterior probability (1) variational bayesian (1) uncertainty quantification (1)