Xinwen Hou

deep reinforcement learning (2) representation learning (1) policy evaluation (1) anomaly detection (1) gradient descent (1) continuous control (1) value function approximation (1) sequence learning (1) policy ensemble (1) hierarchical feature (1) gated mechanism (1) gating mechanism (1) target network (1) highway network (1) neural network (1) feature restoration (1) q-network regularization (1) ensemble reinforcement learning (1) template guidance (1) bottleneck compression (1)