Can Pre-Trained Text-to-Image Models Generate Visual Goals for Reinforcement Learning?

Jialu Gao Kaizhe Hu Guowei Xu Huazhe Xu

Published in: CoRR (2023)

Keyphrases

pre trained
reinforcement learning
input image
image classification
single image
image segmentation
image features
statistical model
image content
probabilistic model
training examples
high resolution
data sets
training data
image retrieval
super resolution
feature points
pixel level
machine learning