Han Zheng

deep reinforcement learning (2) post-training quantization (1) sample efficiency (1) offline reinforcement learning (1) image generation (1) conformal prediction (1) uncertainty quantification (1) preference alignment (1) multimodal learning (1) policy learning (1) reinforcement learning from human feedback (1) value iteration (1) continuous control (1) off-policy learning (1) domain knowledge (1) online reinforcement learning (1) diffusion model (1) reward model (1) cooperative learning (1) heterogeneous agent (1)