English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Machine learning techniques are playing more and more important roles infinance market investment. However, finance quantitative modeling withconventional supervised learning approaches has a number of limitations. Thedevelopment of deep reinforcement learning techniques is partially addressingthese issues. Unfortunately, the steep learning curve and the difficulty inquick modeling and agile development are impeding finance researchers fromusing deep reinforcement learning in quantitative trading. In this paper, wepropose an RLOps in finance paradigm and present a FinRL-Podracer framework toaccelerate the development pipeline of deep reinforcement learning (DRL)-driventrading strategy and to improve both trading performance and trainingefficiency. FinRL-Podracer is a cloud solution that features high performanceand high scalability and promises continuous training, continuous integration,and continuous delivery of DRL-driven trading strategies, facilitating a rapidtransformation from algorithmic innovations into a profitable trading strategy.First, we propose a generational evolution mechanism with an ensemble strategyto improve the trading performance of a DRL agent, and schedule the training ofa DRL algorithm onto a GPU cloud via multi-level mapping. Then, we carry outthe training of DRL components with high-performance optimizations on GPUs.Finally, we evaluate the FinRL-Podracer framework for a stock trend predictiontask on an NVIDIA DGX SuperPOD cloud. FinRL-Podracer outperforms three popularDRL libraries Ray RLlib, Stable Baseline 3 and FinRL, i.e., 12% \sim 35%improvements in annual return, 0.1 \sim 0.6 improvements in Sharpe ratio and 3times \sim 7 times speed-up in training time. We show the high scalability bytraining a trading agent in 10 minutes with $80$ A100 GPUs, on NASDAQ-100constituent stocks with minute-level data over 10 years.

FinRL-Podracer: High Performance and Scalable Deep Reinforcement Learning for Quantitative Finance