Intrinsically Motivated Self-supervised Learning in Reinforcement Learning
Yue Zhao,Chenzhuang Du,Hang Zhao,Tiejun Li,Yue Zhao,Chenzhuang Du,Hang Zhao,Tiejun Li
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 utiliz...
