Yasin Abbasi Yadkori

regret bound (9) online learning (6) multi-armed bandit (4) adversarial learning (3) contextual bandit (3) linear bandit (2) upper confidence bound (2) online decision making (2) minimax optimization (2) minimax strategy (2) model selection (1) sample complexity (1) pac learning (1) posterior sampling (1) epistemic uncertainty (1) regret analysis (1) uncertainty quantification (1) regret minimization (1) policy optimization (1) reinforcement learning (1)