arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2001.01102cs.LGstat.ML
收藏

MushroomRL:简化强化学习研究

MushroomRL: Simplifying Reinforcement Learning Research

TU Darmstadt(达姆施塔特工业大学);Politecnico di Milano(米兰理工大学);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)

Carlo D'Eramo, Davide Tateo, Andrea Bonarini, Marcello Restelli, Jan Peters

摘要:

MushroomRL是一个开源Python库,旨在简化强化学习(RL)实验的实现和运行过程。与其他可用的库相比,MushroomRL的创建旨在提供一个全面而灵活的框架,以最大限度地减少实现和测试新RL方法的工作量。事实上,MushroomRL的架构是以内置的方式构建的,RL问题的每个组件都已经提供,大多数时候用户只能专注于实现自己的算法和实验。其结果是一个图书馆,RL研究人员可以显着受益于他们的作品的实证分析的关键阶段。MushroomRL稳定代码、教程和文档可以在https://github.com/MushroomRL/mushroom-rl上找到。

英文摘要:

MushroomRL is an open-source Python library developed to simplify the process of implementing and running Reinforcement Learning (RL) experiments. Compared to other available libraries, MushroomRL has been created with the purpose of providing a comprehensive and flexible framework to minimize the effort in implementing and testing novel RL methodologies. Indeed, the architecture of MushroomRL is built in such a way that every component of an RL problem is already provided, and most of the time users can only focus on the implementation of their own algorithms and experiments. The result is a library from which RL researchers can significantly benefit in the critical phase of the empirical analysis of their works. MushroomRL stable code, tutorials and documentation can be found at https://github.com/MushroomRL/mushroom-rl.

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。

↑