Paul Weng

multi-armed bandit (3) regret bound (3) fair policy (2) deep reinforcement learning (2) reward function (2) policy gradient (2) multi-objective optimization (2) offline reinforcement learning (1) epistemic uncertainty (1) sample efficiency (1) robotic manipulation (1) policy optimization (1) preference learning (1) policy learning (1) reinforcement learning (1) query selection (1) regret minimization (1) imitation learning (1) model-based reinforcement learning (1) reinforcement learning from human feedback (1)