arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.07910cs.LGcs.AI
收藏

SaLinA:Agent的顺序学习

SaLinA: Sequential Learning of Agents

Facebook(脸书)

Ludovic Denoyer, Alfredo de la Fuente, Song Duong, Jean-Baptiste Gaya, Pierre-Alexandre Kamienny, Daniel H. Thompson

摘要:

SaLinA是一个简单的库,可以轻松实现复杂的顺序学习模型,包括强化学习算法。它是作为PyTorch的扩展构建的:使用\SALINA{}编码的算法可以在几分钟内被PyTorch用户理解并轻松修改。此外,SaLinA在训练和测试时自然地与多个CPU和GPU一起工作,因此非常适合大规模训练用例。与现有的RL库相比,SaLinA的采用成本非常低,并且可以捕获各种设置(基于模型的RL,批量RL,分层RL,多代理RL等)。但是SaLinA不仅针对RL实践者,它还旨在为任何深度学习程序员提供顺序学习功能。

英文摘要:

SaLinA is a simple library that makes implementing complex sequential learning models easy, including reinforcement learning algorithms. It is built as an extension of PyTorch: algorithms coded with \SALINA{} can be understood in few minutes by PyTorch users and modified easily. Moreover, SaLinA naturally works with multiple CPUs and GPUs at train and test time, thus being a good fit for the large-scale training use cases. In comparison to existing RL libraries, SaLinA has a very low adoption cost and capture a large variety of settings (model-based RL, batch RL, hierarchical RL, multi-agent RL, etc.). But SaLinA does not only target RL practitioners, it aims at providing sequential learning capabilities to any deep learning programmer.

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。

↑