Yonathan Efroni

reinforcement learning (12) regret bound (6) online learning (5) policy learning (5) contextual bandit (4) sample complexity (4) dynamic programming (4) policy optimization (3) policy iteration (3) markov decision process (3) optimal policy (3) multi-task learning (2) greedy policy (2) partial observability (2) policy improvement (2) multi-armed bandit (2) value iteration (2) model-based reinforcement learning (2) deep reinforcement learning (2) adversarial robustness (2)