Yifei Ma

active learning (4) reinforcement learning (3) contextual bandit (2) preference learning (2) imitation learning (1) policy optimization (1) representation learning (1) preference elicitation (1) knowledge distillation (1) image retrieval (1) information retrieval (1) multimodal learning (1) multi-modal learning (1) markov decision process (1) importance sampling (1) gaussian process (1) graph-based learning (1) algorithm design (1) label propagation (1) off-policy evaluation (1)