Nadav Merlis

regret bound (12) online learning (7) reinforcement learning (5) multi-armed bandit (4) markov decision process (3) thompson sampling (3) contextual bandit (3) stochastic optimization (2) deep q-network (2) online algorithm (2) regret analysis (2) model-based reinforcement learning (2) constraint satisfaction (1) dynamic programming (1) exploration-exploitation tradeoff (1) offline reinforcement learning (1) deep reinforcement learning (1) policy learning (1) autonomous driving (1) greedy policy (1)