Dragonfly是模块化强化学习库，支持快速实验与参数调试。
Dragonfly: a modular deep reinforcement learning library
- 通过JSON序列化实现组件自由替换，降低开发维护成本。
- 在标准基准测试中性能优于现有方法，适配高耗时仿真环境。
- 适合需要快速迭代的强化学习研究者和仿真场景开发者。
Dragonfly是一个专注于模块化的深度强化学习库，旨在简化实验与开发流程。其基于JSON序列化设计，可轻松更换构建模块并执行参数扫描，同时减少代码维护工作量。部分功能专为计算密集型环境（如数值模拟）优化。在使用常见基准测试的标准智能体上，其性能与文献水平相当甚至更优。
原文摘要 · Abstract (English)
Dragonfly is a deep reinforcement learning library focused on modularity, in order to ease experimentation and developments. It relies on a json serialization that allows to swap building blocks and perform parameter sweep, while minimizing code maintenance. Some of its features are specifically designed for CPU-intensive environments, such as numerical simulations. Its performance on standard agents using common benchmarks compares favorably with the literature.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。