Yan Duan

deep reinforcement learning (2) continuous control (2) intrinsic motivation (2) density estimation (2) representation learning (2) autoregressive model (2) exploration bonus (2) image generation (1) transfer learning (1) few-shot learning (1) variational inference (1) robotic manipulation (1) policy gradient (1) policy learning (1) semi-supervised learning (1) state space exploration (1) imitation learning (1) mutual information (1) sampling distribution (1) approximate inference (1)