Maximilian Igl

generative model (2) evidence lower bound (2) variational inference (2) approximate inference (1) behavior cloning (1) transfer learning (1) domain generalization (1) information bottleneck (1) multitask learning (1) hierarchical reinforcement learning (1) trajectory tracking (1) markov decision process (1) covariate shift (1) partially observable markov decision process (1) continuous control (1) particle filtering (1) exploration exploitation tradeoff (1) bayes-optimal policy (1) locomotion control (1) multi-task learning (1)