Yihan Zhou

active learning (1) deep reinforcement learning (1) reinforcement learning (1) binary classification (1) sample complexity (1) code generation (1) policy learning (1) visual grounding (1) model predictive control (1) partially observable markov decision process (1) agnostic learning (1) online convex optimization (1) quadratic programming (1) disagreement coefficient (1) lipschitz continuity (1) online mirror descent (1) regret bound (1) generative simulation (1) factored markov decision process (1) simulation code generation (1)