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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep reinforcement learning (DRL) has shown huge potentials in buildingfinancial market simulators recently. However, due to the highly complex anddynamic nature of real-world markets, raw historical financial data ofteninvolve large noise and may not reflect the future of markets, degrading thefidelity of DRL-based market simulators. Moreover, the accuracy of DRL-basedmarket simulators heavily relies on numerous and diverse DRL agents, whichincreases demand for a universe of market environments and imposes a challengeon simulation speed. In this paper, we present a FinRL-Meta framework thatbuilds a universe of market environments for data-driven financialreinforcement learning. First, FinRL-Meta separates financial data processingfrom the design pipeline of DRL-based strategy and provides open-source dataengineering tools for financial big data. Second, FinRL-Meta provides hundredsof market environments for various trading tasks. Third, FinRL-Meta enablesmultiprocessing simulation and training by exploiting thousands of GPU cores.Our codes are available online athttps://github.com/AI4Finance-Foundation/FinRL-Meta.

FinRL-Meta: A Universe of Near-Real Market Environments for Data-Driven Deep Reinforcement Learning in Quantitative Finance