AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning

Qi Wang, Mian Wu, Yuyang Zhang, Mingqi Yuan, Wenyao Zhang, Haoxiang You, Yunbo Wang, Xin Jin, Xiaokang Yang, Wenjun Zeng

CVPR 2026 · Reinforcement learning › Visual and representation RL · approach: Goal-conditioned policy learning · 2 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
use GenReward video-diffusion goal reward instead of the environment dense rewardDreamerV3 · Meta-World Pick Out of Holeepisode return: 193 -> 582Improved
use GenReward instead of the environment dense rewardDreamerV3 · Meta-World Bin Pickingepisode return: 398 -> 822Improved
use GenReward instead of the environment dense rewardDreamerV3 · Meta-World Shelf Placeepisode return: 154 -> 814Improved
add video-level reward (video encoder similarity to generated goal video) (ablation)GenReward · Meta-World Pick Placeepisode returnImproved
add frame-level forward-backward reward with CLIP-selected goal frame (ablation)GenReward · Meta-World Pick Placeepisode returnImproved
increase video-level reward weight alpha too far or too low (ablation)GenReward · Meta-World Pick Placeepisode returnMixed
use goal videos generated from RT-1 or RLBench instead of Bridge (ablation)GenReward · Meta-World Pick Placeepisode returnImproved

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