CCLF: A Contrastive-Curiosity-Driven Learning Framework for Sample-Efficient Reinforcement Learning. (arXiv:2205.00943v2 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2205.00943

In reinforcement learning (RL), it is challenging to learn directly from
high-dimensional observations, where data augmentation has recently been shown
to remedy this via encoding invariances from raw pixels. Nevertheless, we
empirically find that not all samples are equally important and hence simply
injecting more augmented inputs may instead cause instability in Q-learning. In
this paper, we approach this problem systematically by developing a
model-agnostic Contrastive-Curiosity-Driven Learning Framework (CCLF), which
can fully exploit sample importance and improve learning efficiency in …

arxiv framework learning reinforcement reinforcement learning