Tanguy Urvoy

multi-armed bandit (3) tabular datum (2) regret bound (2) synthetic data detection (2) few-shot learning (1) risk management (1) deep reinforcement learning (1) domain adaptation (1) reinforcement learning (1) sample complexity (1) privacy preservation (1) policy learning (1) paraphrase generation (1) exploration exploitation (1) continuous state space (1) domain generalization (1) monte-carlo tree search (1) partial feedback (1) multi-objective optimization (1) sequential optimization (1)