David Lindner

sample complexity (2) inverse reinforcement learning (2) online learning (1) preference learning (1) constrained reinforcement learning (1) model evaluation (1) model architecture (1) constrained markov decision process (1) model analysis (1) ai safety (1) convex optimization (1) bayesian model (1) reward function (1) reward learning (1) sample efficiency (1) multi-armed bandit (1) information gain (1) linear bandit (1) safety constraint (1) active learning (1)