Carlo D'Eramo

reinforcement learning (2) offline reinforcement learning (1) self-paced learning (1) probabilistic modeling (1) variational inference (1) function approximation (1) hierarchical reinforcement learning (1) markov decision process (1) value function (1) value iteration (1) partially observable markov decision process (1) exploration exploitation (1) optimal value function (1) temporal-difference learning (1) sequential decision-making (1) monte-carlo tree search (1) approximate value iteration (1) online reinforcement learning (1) learning progress (1) deep reinforcement learning (1)