Tongzhou Mu

reinforcement learning (2) stochastic gradient descent (1) sample efficiency (1) imitation learning (1) robotic manipulation (1) transfer learning (1) convex optimization (1) self-supervised learning (1) data augmentation (1) policy learning (1) visual representation (1) embodied ai (1) visual reinforcement learning (1) task generalization (1) empirical risk minimization (1) robot learning (1) large-scale learning (1) coordinate descent (1) block coordinate descent (1) accelerated gradient (1)