Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Zha, Jiale"'
We propose a new reinforcement learning (RL) formulation for training continuous-time score-based diffusion models for generative AI to generate samples that maximize reward functions while keeping the generated distributions close to the unknown tar
Externí odkaz:
http://arxiv.org/abs/2409.04832
