Yann Ollivier

temporal difference learning (2) policy optimization (2) privacy attack (1) black-box optimization (1) markov decision process (1) natural gradient (1) discount factor (1) value function (1) probability distribution (1) reward function (1) off-policy learning (1) minimum description length (1) information geometry (1) continuous time (1) adversarial attack (1) black-box attack (1) deep neural network (1) adversarial perturbation (1) generative adversarial network (1) return distribution (1)