Mohammad Sadegh Talebi

regret bound (4) regret minimization (3) markov decision process (3) reinforcement learning (2) sample complexity (1) policy learning (1) automata learning (1) value iteration (1) model-based reinforcement learning (1) markov chain (1) concentration inequality (1) confidence set (1) bandit algorithm (1) average reward (1) model-based algorithm (1) adversarial bandit (1) reward machine (1) decision process (1) variance analysis (1) regular decision process (1)