Zhongmin Cai

reinforcement learning (1) benchmark evaluation (1) non-convex optimization (1) transfer learning (1) natural language generation (1) question generation (1) sequential prediction (1) knowledge graph (1) human-ai collaboration (1) evaluation benchmark (1) policy network (1) hierarchical federated learning (1) model drift (1) bayesian policy reuse (1) non-stationary dynamics (1) meta-task learning (1) human evaluation (1) user behavior (1) automatic evaluation (1) multi-dimensional evaluation (1)