Diffusion models are a class of flexible generative models trained with an approximation to the log-likelihood objective. However, most use cases of diffusion models are not concerned with likelihoods, but instead with downstream objectives such as human-perceived image quality or drug effectiveness. In this paper, we investigate reinforcement learning methods for directly optimizing diffusion models for such objectives. We describe how posing denoising as a multi-step decision-making problem enables a class of policy gradient algorithms, which we refer to as denoising diffusion policy optimization (DDPO), that are more effective than alternative reward-weighted likelihood approaches. Empirically, DDPO is able to adapt text-to-image diffusion models to objectives that are difficult to express via prompting, such as image compressibility, and those derived from human feedback, such as aesthetic quality. Finally, we show that DDPO can improve prompt-image alignment using feedback from a vision-language model without the need for additional data collection or human annotation.

翻译：扩散模型是一类灵活的生成模型，通过近似对数似然目标进行训练。然而，扩散模型的大多数应用场景并不关注似然值，而是侧重于下游目标，例如人类感知的图像质量或药物有效性。本文研究了直接针对此类目标优化扩散模型的强化学习方法。我们阐述了如何将去噪过程构建为多步决策问题，从而能够应用一类策略梯度算法——我们称之为去噪扩散策略优化（DDPO）——该算法比替代的奖励加权似然方法更为有效。实验表明，DDPO能够使文本到图像扩散模型适应难以通过提示表达的目标（如图像压缩性）以及源自人类反馈的目标（如审美质量）。最后，我们证明DDPO可利用视觉语言模型的反馈提升提示-图像对齐度，而无需额外的数据收集或人工标注。