Zero-Shot Stitching in Reinforcement Learning using Relative Representations

arXiv:2404.12917v1 Announce Type: new
Abstract: Visual Reinforcement Learning is a popular and powerful framework that takes full advantage of the Deep Learning breakthrough. However, it is also known that variations in the input (e.g., different colors of the panorama due to the season of the year) or the task (e.g., changing the speed limit for a car to respect) could require complete retraining of the agents. In this work, we leverage recent developments in unifying latent representations to demonstrate that …

abstract arxiv colors cs.ai cs.cv cs.lg deep learning framework however panorama popular reinforcement reinforcement learning stitching type visual zero-shot