FinFlowRL: An Imitation-Reinforcement Learning Framework for Adaptive Stochastic Control in Finance
Yang Li, Zhi Chen
现实世界市场中金融斗争中的传统随机控制方法,因为它们依赖于简化的假设和程式化框架。 此类方法通常在特定的、定义良好的环境中表现良好,但在改变的非静止环境中产生次优结果。 我们介绍了FinFlowRL,这是一个金融最优随机控制的新框架。 该框架从多个专家策略中预训练自适应元策略学习,然后通过噪声空间中的强化学习进行微调,以优化生成过程。 通过采用动作块生成动作序列而不是单个决策,它解决了市场的非马尔科维性质。 FinFlowRL 在不同市场条件下的表现一直优于个别优化的专家。
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 reinforceme...
