Samuel Holt

large language model (3) model predictive control (2) dynamical system (2) preference optimization (1) reinforcement learning from human feedback (1) robot learning (1) model-based reinforcement learning (1) offline learning (1) exponential loss (1) logistic loss (1) loss function (1) policy training (1) continuous-time reinforcement learning (1) interpretable model (1) evolutionary algorithm (1) digital twin (1) physics simulation (1) hybrid modeling (1) convex loss function (1) algorithm discovery (1)