Matthias Schultheis

inverse optimal control (2) bayesian inference (1) deep learning (1) inverse reinforcement learning (1) value function (1) system identification (1) partially observable markov decision process (1) trajectory optimization (1) belief space (1) bayesian experimental design (1) continuous time (1) information gain (1) optimal feedback control (1) hamilton-jacobi-bellman equation (1) partially observable system (1) sample-efficient exploration (1) hyperbolic discounting (1) signal-dependent noise (1) partial observable markov decision process (1) perceptual uncertainty (1)