Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?. (arXiv:2206.05266v2 [cs.LG] UPDATED)

We investigate whether self-supervised learning (SSL) can improve online
reinforcement learning (RL) from pixels. We extend the contrastive
reinforcement learning framework (e.g., CURL) that jointly optimizes SSL and RL
losses and conduct an extensive amount of experiments with various
self-supervised losses. Our observations suggest that the existing SSL
framework for RL fails to bring meaningful improvement over the baselines only
taking advantage of image augmentation when the same amount of data and
augmentation is used. We further perform an evolutionary …

arxiv learning lg reinforcement reinforcement learning self-supervised learning supervised learning