David Budden

online learning (3) gated linear network (3) contextual bandit (2) modular learning (2) catastrophic forgetting (2) neural network (2) dynamic programming (1) offline reinforcement learning (1) continual learning (1) density estimation (1) self-supervised learning (1) deep learning (1) transfer learning (1) reward function (1) few-shot learning (1) robot manipulation (1) reward learning (1) robotic manipulation (1) offline learning (1) batch reinforcement learning (1)