Laura M Smith

unsupervised learning (1) deep reinforcement learning (1) sample efficiency (1) multi-task learning (1) reward modeling (1) offline reinforcement learning (1) self-supervised learning (1) markov decision process (1) quadruped locomotion (1) distribution shift (1) off-policy learning (1) interactive reinforcement learning (1) human feedback (1) preference feedback (1) reward model (1) meta-reinforcement learning (1) model-free reinforcement learning (1) unsupervised pre-training (1) offline meta-reinforcement learning (1) experience transfer (1)