We characterise the problem of abstraction in the context of deep
reinforcement learning. Various well established approaches to analogical
reasoning and associative memory might be brought to bear on this issue, but
they present difficulties because of the need for end-to-end differentiability.
We review developments in AI and machine learning that could facilitate their
adoption.

本文在深度强化学习的背景下对抽象问题进行了阐述，并探讨了 AI 和机器学习发展中的各种方法及其应用的难点。

深度强化学习的抽象化

Abstraction for Deep Reinforcement Learning

We introduce a novel Deep Network architecture that implements the full
feature point handling pipeline, that is, detection, orientation estimation,
and feature description. While previous works have successfully tackled each
one of these problems individually, we show how to learn to do all three in a
unified manner while preserving end-to-end differentiability. We then
demonstrate that our Deep pipeline outperforms state-of-the-art methods on a
number of benchmark datasets, without the need of retraining.

介绍一种新颖的深度网络架构，实现了完整的特征点处理流程，包括检测、方向估计和特征描述，并展示了其在多个基准数据集上超过现有方法的性能表现，同时不需要重新训练。