Carlo D’Eramo

Statistics (1)

reinforcement learning (2) offline reinforcement learning (1) sequential decision-making (1) policy optimization (1) curriculum learning (1) optimal transport (1) policy learning (1) exploration-exploitation tradeoff (1) value iteration (1) fitted q-iteration (1) gaussian approximation (1) sequential learning (1) monte-carlo tree search (1) action-value function (1) offline learning (1) approximate value iteration (1) regret bound (1) task distribution (1) game ai (1) convex regularization (1)