Sequoia：一个统一持续学习研究的软件框架
Sequoia: A Software Framework to Unify Continual Learning Research
AI总结：
本文提出以假设集合刻画持续学习设置的树形分类体系，并发布统一 CSL 与 CRL 设置、方法及复用机制的开源软件框架 Sequoia。
摘要：
持续学习（Continual Learning，CL）领域旨在开发通过与非平稳环境交互、随时间积累知识与技能的算法。在实践中，存在大量评估流程（设置）和算法解决方案（方法），每一种都有其自身可能互不相交的一组假设。这种多样性使得衡量 CL 领域的进展变得困难。我们提出了一种设置分类体系，其中每个设置都被描述为一组假设。从这一视角会产生一个树形层次结构：更通用的设置成为那些具有更严格假设的设置的父节点。这使得利用继承来共享和复用研究成为可能，因为针对某个给定设置开发的方法也可以直接应用于其任意子设置。我们将这一思想实例化为一个名为 Sequoia 的公开可用软件框架，其特点是包含来自持续监督学习（Continual Supervised Learning，CSL）和持续强化学习（Continual Reinforcement Learning，CRL）两个领域的多种多样的设置。除来自外部库的更专门方法外，Sequoia 还包括一套不断扩充、易于扩展和定制的方法。我们希望这一新范式及其首个实现能够帮助统一并加速 CL 研究。您可以访问 www.github.com/lebrice/Sequoia，帮助我们壮大这棵树。
英文摘要：
The field of Continual Learning (CL) seeks to develop algorithms that accumulate knowledge and skills over time through interaction with non-stationary environments. In practice, a plethora of evaluation procedures (settings) and algorithmic solutions (methods) exist, each with their own potentially disjoint set of assumptions. This variety makes measuring progress in CL difficult. We propose a taxonomy of settings, where each setting is described as a set of assumptions. A tree-shaped hierarchy emerges from this view, where more general settings become the parents of those with more restrictive assumptions. This makes it possible to use inheritance to share and reuse research, as developing a method for a given setting also makes it directly applicable onto any of its children. We instantiate this idea as a publicly available software framework called Sequoia, which features a wide variety of settings from both the Continual Supervised Learning (CSL) and Continual Reinforcement Learning (CRL) domains. Sequoia also includes a growing suite of methods which are easy to extend and customize, in addition to more specialized methods from external libraries. We hope that this new paradigm and its first implementation can help unify and accelerate research in CL. You can help us grow the tree by visiting www.github.com/lebrice/Sequoia.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
