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

2025/08/30 by Yang Li, Zhi Chen, Li, Yang +1 · 1 voice
Computer Science · Decision Sciences · Economics, Econometrics and Finance · #Artificial Intelligence (cs.AI) #Complex Systems and Time Series Analysis #Computational Finance (q-fin.CP) #FOS: Computer and information sciences #FOS: Economics and business #Machine Learning (cs.LG) #Reinforcement Learning in Robotics #Stock Market Forecasting Methods #Trading and Market Microstructure (q-fin.TR) #cs.AI #cs.LG #q-fin.CP #q-fin.TR

paper · pdf · doi:10.48550/arxiv.2510.15883

openalex publication_date 2025/08/30 · arxiv published 2025/08/30 · arxiv updated 2025/08/30 · openalex created_date 2025/10/22 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Reinforcement Learning with Action Chunking
• Steering Your Diffusion Policy with Latent Space Reinforcement Learning
• Flow-Based Policy for Online Reinforcement Learning
• Mean Flows for One-step Generative Modeling
• Flow Matching Guide and Code
• Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
• Diffusion policy: Visuomotor policy learning via action diffusion
• Flow Matching for Generative Modeling
• Market Making under a Weakly Consistent Limit Order Book Model
• Proximal Policy Optimization Algorithms
• The Problem of Calibrating an Agent-Based Model of High-Frequency Trading
• Hawkes processes in finance
• Volatility is rough
• The Pricing of Options and Corporate Liabilities
• Fractional Brownian Motions, Fractional Noises and Applications

Discussions

• Yang Li, Zhi Chen: FinFlowRL: An Imitation-Reinforcement Learning Framework for Adaptive Stochastic Control in Finance https://arxiv.org/abs/2510.15883 https://arxiv.org/pdf/2510.15883 https://arxiv.o [bsky, 0 points, 0 comments]

Related

• FinFlowRL: An Imitation-Reinforcement Learning Framework for Adaptive Stochastic Control in Finance
• Robot See, Robot Do: Imitation Reward for Noisy Financial Environments
• Reinforcement Learning: Prediction, Control and Value Function Approximation
• Market Making Strategies with Reinforcement Learning
• FlowOE: Imitation Learning with Flow Policy from Ensemble RL Experts for Optimal Execution under Heston Volatility and Concave Market Impacts