Huayu Chen

diffusion model (2) offline reinforcement learning (2) reinforcement learning (1) adversarial learning (1) imitation learning (1) policy optimization (1) guided sampling (1) preference optimization (1) policy learning (1) language model alignment (1) continuous control (1) reward function (1) reward model (1) energy-based model (1) control theory (1) policy alignment (1) training stability (1) algorithm implementation (1) noise contrastive estimation (1) reward signal (1)