Victor Gabillon

multi-armed bandit (5) regret bound (4) online learning (3) best arm identification (2) stochastic optimization (2) sample complexity (2) gap-based exploration (2) value function (2) approximate dynamic programming (2) simple regret (2) exploration exploitation (2) regret minimization (1) non-convex optimization (1) exploration-exploitation (1) markov chain monte carlo (1) minimax optimization (1) learning theory (1) policy learning (1) policy iteration (1) adversarial learning (1)