Guoqing Liu

reinforcement learning (5) neural network optimization (2) feature learning (2) policy optimization (1) multi-frame processing (1) black-box optimization (1) sparse representation (1) multi-instance learning (1) video sequence (1) geometric deep learning (1) importance sampling (1) policy gradient (1) monte carlo estimation (1) fisher information (1) multi-task learning (1) mutual information (1) policy iteration (1) variance reduction (1) 3d reconstruction (1) unsupervised learning (1)