Visual processing in context of reinforcement learning. (arXiv:2208.12525v1 [cs.LG])

Although deep reinforcement learning (RL) has recently enjoyed many
successes, its methods are still data inefficient, which makes solving numerous
problems prohibitively expensive in terms of data. We aim to remedy this by
taking advantage of the rich supervisory signal in unlabeled data for learning
state representations. This thesis introduces three different representation
learning algorithms that have access to different subsets of the data sources
that traditional RL algorithms use:

(i) GRICA is inspired by independent component analysis (ICA) and …

arxiv context learning lg processing reinforcement reinforcement learning visual processing