Wei Xiong

reinforcement learning from human feedback (5) regret bound (4) diffusion model (4) markov game (3) identity preservation (3) image editing (3) generative adversarial network (2) language model (2) image generation (2) reinforcement learning (2) human feedback (2) adversarial training (2) function approximation (2) reward model (2) policy learning (2) contrastive learning (2) markov decision process (2) minimax optimization (2) offline reinforcement learning (2) multi-armed bandit (2)