Tetsuro Morimura

minimum bayes risk (3) text generation (3) reinforcement learning (2) policy gradient (2) natural gradient (2) language model alignment (2) direct preference optimization (1) preference learning (1) anomaly detection (1) variance reduction (1) utility optimization (1) probability estimation (1) reinforcement learning from human feedback (1) markov decision process (1) gaussian process regression (1) neural machine translation (1) model alignment (1) actor-critic (1) natural policy gradient (1) convex optimization (1)