Intrinsically Motivated Self-supervised Learning in Reinforcement Learning. (arXiv:2106.13970v2 [cs.LG] UPDATED)

In vision-based reinforcement learning (RL) tasks, it is prevalent to assign
auxiliary tasks with a surrogate self-supervised loss so as to obtain more
semantic representations and improve sample efficiency. However, abundant
information in self-supervised auxiliary tasks has been disregarded, since the
representation learning part and the decision-making part are separated. To
sufficiently utilize information in auxiliary tasks, we present a simple yet
effective idea to employ self-supervised loss as an intrinsic reward, called
Intrinsically Motivated Self-Supervised learning in Reinforcement learning …

arxiv learning reinforcement reinforcement learning self-supervised learning supervised learning