Dynamic datasets and market environments for financial reinforcement learning
文献类型：期刊论文
| 作者 | Liu, Xiao-Yang1; Xia, Ziyi1; Yang, Hongyang1; Gao, Jiechao2; Zha, Daochen3; Zhu, Ming4,5 ; Wang, Christina Dan6; Wang, Zhaoran7; Guo, Jian8
|
| 刊名 | MACHINE LEARNING
 |
| 出版日期 | 2024-02-26 |
| 页码 | 45 |
| 关键词 | Financial reinforcement learning FinRL Dynamic dataset Market environment AI4Finance Open finance |
| ISSN号 | 0885-6125 |
| DOI | 10.1007/s10994-023-06511-w |
| 通讯作者 | Liu, Xiao-Yang(xl2427@columbia.edu) |
| 英文摘要 | The financial market is a particularly challenging playground for deep reinforcement learning due to its unique feature of dynamic datasets. Building high-quality market environments for training financial reinforcement learning (FinRL) agents is difficult due to major factors such as the low signal-to-noise ratio of financial data, survivorship bias of historical data, and model overfitting. In this paper, we present an updated version of FinRL-Meta, a data-centric and openly accessible library that processes dynamic datasets from real-world markets into gym-style market environments and has been actively maintained by the AI4Finance community. First, following a DataOps paradigm, we provide hundreds of market environments through an automatic data curation pipeline. Second, we provide homegrown examples and reproduce popular research papers as stepping stones for users to design new trading strategies. We also deploy the library on cloud platforms so that users can visualize their own results and assess the relative performance via community-wise competitions. Third, we provide dozens of Jupyter/Python demos organized into a curriculum and a documentation website to serve the rapidly growing community. The codes are available at https://github.com/AI4Finance-Foundation/FinRL-Meta |
| WOS关键词 | LEVEL ; GAME ; GO |
| 资助项目 | National Natural Science Foundations of China[61902387] ; Shanghai Frontiers Science Center of Artificial Intelligence and Deep Learning, NYU Shanghai ; Shanghai China[200122] ; National Natural ScienceFoundation of China (NNSFC)[12271363] ; NOT a recommendation |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001170375400001 |
| 出版者 | SPRINGER |
| 资助机构 | National Natural Science Foundations of China ; Shanghai Frontiers Science Center of Artificial Intelligence and Deep Learning, NYU Shanghai ; Shanghai China ; National Natural ScienceFoundation of China (NNSFC) ; NOT a recommendation |
| 源URL | [http://ir.ia.ac.cn/handle/173211/57806]  |
| 专题 | 综合信息系统研究中心_飞行器智能技术 |
| 通讯作者 | Liu, Xiao-Yang |
| 作者单位 | 1.Columbia Univ, New York, NY 10027 USA 2.Univ Virginia, Charlottesville, VA USA 3.Rice Univ, Houston, TX USA 4.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 5.Univ Chinese Acad Sci, Beijing, Peoples R China 6.New York Univ Shanghai, Shanghai, Peoples R China 7.Northwestern Univ, Evanston, IL USA 8.Int Digital Econ Acad, IDEA Res, Shenzhen, Peoples R China |
| 推荐引用方式 GB/T 7714 | Liu, Xiao-Yang,Xia, Ziyi,Yang, Hongyang,et al. Dynamic datasets and market environments for financial reinforcement learning[J]. MACHINE LEARNING,2024:45. |
| APA | Liu, Xiao-Yang.,Xia, Ziyi.,Yang, Hongyang.,Gao, Jiechao.,Zha, Daochen.,...&Guo, Jian.(2024).Dynamic datasets and market environments for financial reinforcement learning.MACHINE LEARNING,45. |
| MLA | Liu, Xiao-Yang,et al."Dynamic datasets and market environments for financial reinforcement learning".MACHINE LEARNING (2024):45. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。