Hi-DARTS: Hierarchical Dynamically Adapting Reinforcement Trading System
This work addresses the trade-off between efficiency and responsiveness in trading systems for financial markets, representing an incremental improvement with specific performance gains.
The paper tackled the problem of balancing computational efficiency and market responsiveness in autonomous trading systems by proposing Hi-DARTS, a hierarchical multi-agent reinforcement learning framework that dynamically adapts trading frequency based on market volatility, achieving a cumulative return of 25.17% with a Sharpe Ratio of 0.75 in back-testing on AAPL stock.
Conventional autonomous trading systems struggle to balance computational efficiency and market responsiveness due to their fixed operating frequency. We propose Hi-DARTS, a hierarchical multi-agent reinforcement learning framework that addresses this trade-off. Hi-DARTS utilizes a meta-agent to analyze market volatility and dynamically activate specialized Time Frame Agents for high-frequency or low-frequency trading as needed. During back-testing on AAPL stock from January 2024 to May 2025, Hi-DARTS yielded a cumulative return of 25.17% with a Sharpe Ratio of 0.75. This performance surpasses standard benchmarks, including a passive buy-and-hold strategy on AAPL (12.19% return) and the S&P 500 ETF (SPY) (20.01% return). Our work demonstrates that dynamic, hierarchical agents can achieve superior risk-adjusted returns while maintaining high computational efficiency.