Zhihan Liu

sublinear regret (2) reinforcement learning from human feedback (2) adversarial learning (1) offline reinforcement learning (1) policy optimization (1) game theory (1) direct preference optimization (1) language model alignment (1) markov decision process (1) model alignment (1) nash equilibrium (1) model-based reinforcement learning (1) linear function approximation (1) regret bound (1) reward model (1) welfare maximization (1) model-free reinforcement learning (1) adversarial agent (1) competitive equilibrium (1) social welfare (1)