AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Extracting Reward Functions from Diffusion Models

Felipe Pinto Coelho Nuti, Tim Franzmeyer, Joao F. Henriques

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: In-context and adaptive RL · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Steer the medium-replay base diffusion model with the learned relative rewardLocomotion diffusion models · Hopper, HalfCheetah, and Walker2DperformanceImproved
Steer the Walker2D base model with the learned relative rewardWalker2D diffusion model · Walker2Dperformance relative to unsteered model: 36.17% relative improvementImproved
Apply the learned relative reward to a new medium-performance diffusion model unseen during reward trainingLocomotion diffusion models · Locomotion domainsperformanceImproved
Learn a relative reward from Safe Stable Diffusion and base Stable DiffusionStable Diffusion image generation · I2P prompt datasetsafe-versus-base image classification accuracy: over 90%Improved
Reduce the training dataset size (ablation)Relative reward estimator · Maze2DperformanceHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy