Samuele Tosatto

policy gradient (4) sample efficiency (3) reinforcement learning (3) off-policy learning (2) bellman equation (2) sparsity prior (1) fitted q-iteration (1) temporal-difference learning (1) action-value function (1) offline learning (1) approximate value iteration (1) world model (1) proximal policy optimization (1) dynamics model (1) causal graph (1) model-free learning (1) boosting procedure (1) regression technique (1) gradient critic (1) reward gradient (1)