Manuel Haußmann

offline reinforcement learning (1) variational inference (1) bayesian inference (1) epistemic uncertainty (1) model-based reinforcement learning (1) moment matching (1) stochastic differential equation (1) uncertainty propagation (1) pessimistic value iteration (1) bellman target (1) bayesian neural network (1) evidence lower bound (1) reparameterization trick (1) pac-bayesian theory (1) neural network (1) deterministic approximation (1) sampling-free inference (1) variance backpropagation (1) probabilistic weight (1) deterministic uncertainty propagation (1)