Nuowen Kan

federated learning (1) deep reinforcement learning (1) sample efficiency (1) transfer learning (1) bayesian inference (1) mutual information (1) posterior inference (1) value function estimation (1) off-policy learning (1) generalization bound (1) meta-reinforcement learning (1) sparse reward (1) camera control (1) importance weight (1) gibbs posterior (1) actor-critic framework (1) expert trajectory regularization (1) focus prediction (1) trajectory regularization (1)