Daniel S. Brown

inverse reinforcement learning (5) reward function (3) preference learning (3) imitation learning (2) policy learning (2) active learning (2) human feedback (2) interactive learning (1) sim-to-real transfer (1) reinforcement learning (1) epistemic uncertainty (1) autonomous driving (1) optimal control (1) model predictive control (1) feature selection (1) domain randomization (1) human-robot interaction (1) bayesian inference (1) out-of-distribution generalization (1) budget-aware learning (1)