David Krueger

reinforcement learning (3) world model (2) large language model (2) out-of-distribution generalization (2) causal inference (2) domain generalization (1) group theory (1) adversarial robustness (1) neural network interpretability (1) model safety (1) feature learning (1) loss landscape (1) model evaluation (1) reinforcement learning from human feedback (1) probability distribution (1) covariate shift (1) model-based reinforcement learning (1) reward function (1) action prediction (1) data augmentation (1)