VARD: Efficient and Dense Fine-Tuning for Diffusion Models with Value-based RL
This addresses the problem of stable and efficient fine-tuning for diffusion models in AI, offering a novel method for handling non-differentiable rewards, though it is incremental in advancing RL applications in this domain.
The paper tackles the challenge of fine-tuning diffusion models with reinforcement learning (RL) by proposing VARD, which uses a value function to provide dense supervision, resulting in improved training efficiency and better trajectory guidance for non-differentiable rewards.
Diffusion models have emerged as powerful generative tools across various domains, yet tailoring pre-trained models to exhibit specific desirable properties remains challenging. While reinforcement learning (RL) offers a promising solution,current methods struggle to simultaneously achieve stable, efficient fine-tuning and support non-differentiable rewards. Furthermore, their reliance on sparse rewards provides inadequate supervision during intermediate steps, often resulting in suboptimal generation quality. To address these limitations, dense and differentiable signals are required throughout the diffusion process. Hence, we propose VAlue-based Reinforced Diffusion (VARD): a novel approach that first learns a value function predicting expection of rewards from intermediate states, and subsequently uses this value function with KL regularization to provide dense supervision throughout the generation process. Our method maintains proximity to the pretrained model while enabling effective and stable training via backpropagation. Experimental results demonstrate that our approach facilitates better trajectory guidance, improves training efficiency and extends the applicability of RL to diffusion models optimized for complex, non-differentiable reward functions.