ReCoRe: Regularized Contrastive Representation Learning of World Model

arXiv:2312.09056v2 Announce Type: replace
Abstract: While recent model-free Reinforcement Learning (RL) methods have demonstrated human-level effectiveness in gaming environments, their success in everyday tasks like visual navigation has been limited, particularly under significant appearance variations. This limitation arises from (i) poor sample efficiency and (ii) over-fitting to training scenarios. To address these challenges, we present a world model that learns invariant features using (i) contrastive unsupervised learning and (ii) an intervention-invariant regularizer. Learning an explicit representation of the world dynamics …

abstract arxiv cs.ai cs.cv cs.lg cs.ro efficiency environments free gaming human navigation reinforcement reinforcement learning representation representation learning sample stat.ml success tasks training type visual visual navigation world world model