Sign in

Diffusion Reward: Learning Rewards via Conditional Video Diffusion

By Tao Huang and others at
LogoChinese University of Hong Kong
and
LogoUniversity of Hong Kong
Learning rewards from expert videos offers an affordable and effective solution to specify the intended behaviors for reinforcement learning (RL) tasks. In this work, we propose Diffusion Reward, a novel framework that learns rewards from expert videos via conditional video diffusion models for solving complex visual RL problems. Our key... Show more
August 9, 2024
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
Diffusion Reward: Learning Rewards via Conditional Video Diffusion
Click on play to start listening