Feiyang Pan

policy gradient (3) reinforcement learning (3) extractive summarization (2) text summarization (2) model-based reinforcement learning (2) convolutional neural network (2) constrained reinforcement learning (1) subspace learning (1) variational inference (1) monte carlo sampling (1) gradient descent (1) canonical correlation analysis (1) exploration exploitation (1) continuous control (1) policy learning (1) hierarchical model (1) multi-view learning (1) constraint satisfaction (1) knowledge distillation (1) sentiment analysis (1)