Yifang Chen

active learning (5) reinforcement learning (3) representation learning (3) contextual bandit (3) multi-task learning (3) dynamic regret (2) regret bound (2) linear mdp (2) sample complexity (2) pac learning (1) multimodal learning (1) preference learning (1) adversarial learning (1) transfer learning (1) corruption robustness (1) binary classification (1) robust reinforcement learning (1) language model alignment (1) episodic learning (1) model merging (1)