Ahmed Touati

policy optimization (2) value function (2) contextual bandit (2) variational inference (2) representation learning (2) policy evaluation (2) deep reinforcement learning (2) temporal difference learning (2) reinforcement learning (2) thompson sampling (2) reward function (1) state representation (1) discount factor (1) off-policy learning (1) convergence guarantee (1) markov decision process (1) linear convergence (1) convex-concave saddle-point (1) linear function approximation (1) function approximation (1)