Gregory Wayne

model-based reinforcement learning (2) variational autoencoder (2) deep reinforcement learning (2) reinforcement learning (1) semi-supervised learning (1) temporal difference learning (1) catastrophic forgetting (1) variational inference (1) density estimation (1) policy gradient (1) motor control (1) language modeling (1) visual grounding (1) lyapunov function (1) continuous control (1) value function (1) online learning (1) variance reduction (1) attractor dynamics (1) continual learning (1)