FinFlowRL: An Imitation-Reinforcement Learning Framework for Adaptive Stochastic Control in Finance

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Yang, Chen, Zhi
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912656572547072
author Li, Yang
Chen, Zhi
author_facet Li, Yang
Chen, Zhi
contents Traditional stochastic control methods in finance struggle in real world markets due to their reliance on simplifying assumptions and stylized frameworks. Such methods typically perform well in specific, well defined environments but yield suboptimal results in changed, non stationary ones. We introduce FinFlowRL, a novel framework for financial optimal stochastic control. The framework pretrains an adaptive meta policy learning from multiple expert strategies, then finetunes through reinforcement learning in the noise space to optimize the generative process. By employing action chunking generating action sequences rather than single decisions, it addresses the non Markovian nature of markets. FinFlowRL consistently outperforms individually optimized experts across diverse market conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2510_15883
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FinFlowRL: An Imitation-Reinforcement Learning Framework for Adaptive Stochastic Control in Finance
Li, Yang
Chen, Zhi
Computational Finance
Artificial Intelligence
Machine Learning
Trading and Market Microstructure
Traditional stochastic control methods in finance struggle in real world markets due to their reliance on simplifying assumptions and stylized frameworks. Such methods typically perform well in specific, well defined environments but yield suboptimal results in changed, non stationary ones. We introduce FinFlowRL, a novel framework for financial optimal stochastic control. The framework pretrains an adaptive meta policy learning from multiple expert strategies, then finetunes through reinforcement learning in the noise space to optimize the generative process. By employing action chunking generating action sequences rather than single decisions, it addresses the non Markovian nature of markets. FinFlowRL consistently outperforms individually optimized experts across diverse market conditions.
title FinFlowRL: An Imitation-Reinforcement Learning Framework for Adaptive Stochastic Control in Finance
topic Computational Finance
Artificial Intelligence
Machine Learning
Trading and Market Microstructure
url https://arxiv.org/abs/2510.15883