Chenlu Ye

function approximation (2) uncertainty weighting (2) markov decision process (2) reinforcement learning (2) policy learning (1) corruption robustness (1) minimax optimization (1) reinforcement learning from human feedback (1) model uncertainty (1) reward function (1) human feedback (1) regret bound (1) contextual bandit (1) adversarial corruption (1) language model (1) uncertainty estimation (1) softmax regression (1) large language model (1) active learning (1) corruption-robust algorithm (1)