Jan Leike

preference learning (3) reward function (3) inverse reinforcement learning (2) reinforcement learning (2) reward model (2) deep reinforcement learning (2) reward learning (2) human preference (2) sequential decision making (1) reinforcement learning from human feedback (1) bayesian inference (1) ai safety (1) model alignment (1) trajectory optimization (1) language model alignment (1) imitation learning (1) value of information (1) demonstration learning (1) sequence prediction (1) kolmogorov complexity (1)