PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 5, 20240 citationsOpen Access

Pixel-wise RL on Diffusion Models: Reinforcement Learning from Rich Feedback

View Full Paper
MKMo KordzanganehDKDanial KeshvaryNANariman Arian

Key Points

Key points are not available for this paper at this time.

Abstract

Latent diffusion models are the state-of-the-art for synthetic image generation. To align these models with human preferences, training the models using reinforcement learning on human feedback is crucial. Black et. al 2024 introduced denoising diffusion policy optimisation (DDPO), which accounts for the iterative denoising nature of the generation by modelling it as a Markov chain with a final reward. As the reward is a single value that determines the model's performance on the entire image, the model has to navigate a very sparse reward landscape and so requires a large sample count. In this work, we extend the DDPO by presenting the Pixel-wise Policy Optimisation (PXPO) algorithm, which can take feedback for each pixel, providing a more nuanced reward to the model.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Kordzanganeh et al. (2024) studied this question.

synapsesocial.com/papers/68e70547b6db64358767f296https://doi.org/10.48550/arxiv.2404.04356
Ask AI
Helpful
Bookmark
Share
View Full Paper