Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2509.17964 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909799732477952 |
|---|---|
| author | Li, Yang Chen, Zhi Yang, Steve Y. Zhang, Ruixun |
| author_facet | Li, Yang Chen, Zhi Yang, Steve Y. Zhang, Ruixun |
| contents | Traditional stochastic control methods in finance rely on simplifying assumptions that often fail in real world markets. While these methods work well in specific, well defined scenarios, they underperform when market conditions change. We introduce FinFlowRL, a novel framework for financial stochastic control that combines imitation learning with reinforcement learning. The framework first pretrains an adaptive meta policy by learning from multiple expert strategies, then finetunes it through reinforcement learning in the noise space to optimize the generation process. By employing action chunking, that is generating sequences of actions rather than single decisions, it addresses the non Markovian nature of financial markets. FinFlowRL consistently outperforms individually optimized experts across diverse market conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17964 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FinFlowRL: An Imitation-Reinforcement Learning Framework for Adaptive Stochastic Control in Finance Li, Yang Chen, Zhi Yang, Steve Y. Zhang, Ruixun Computational Finance Traditional stochastic control methods in finance rely on simplifying assumptions that often fail in real world markets. While these methods work well in specific, well defined scenarios, they underperform when market conditions change. We introduce FinFlowRL, a novel framework for financial stochastic control that combines imitation learning with reinforcement learning. The framework first pretrains an adaptive meta policy by learning from multiple expert strategies, then finetunes it through reinforcement learning in the noise space to optimize the generation process. By employing action chunking, that is generating sequences of actions rather than single decisions, it addresses the non Markovian nature of financial 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 |
| url | https://arxiv.org/abs/2509.17964 |