xLSTM networks enhance deep reinforcement learning for automated stock trading

Researchers have developed a new automated stock trading system utilizing Extended Long Short-Term Memory (xLSTM) networks combined with deep reinforcement learning (DRL). This approach aims to overcome the limitations of traditional LSTMs in handling long-term dependencies and dynamic market conditions. Experiments showed that the xLSTM-based DRL model outperformed standard LSTM models across several key trading metrics, including cumulative return and Sharpe ratio. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Introduces a novel architecture for DRL-based financial trading, potentially improving algorithmic strategy performance.

RANK_REASON Academic paper detailing a new approach to automated stock trading using xLSTM networks.

Read on arXiv cs.LG →

• xLSTM
• LSTM
• DRL
• PPO
• arXiv

• paper
• other