About this document

Deep RL for Dynamic Crypto Portfolio Management by andrew910309 is a document available to read on EtoBox.

This paper presents a novel portfolio management method utilizing deep reinforcement learning (RL) for dynamic cryptocurrency markets with varying numbers of assets. The proposed architecture adapts to new assets without requiring additional training and minimizes transaction costs through an integrated algorithm for optimal transactions. Testing on a large cryptocurrency market dataset demonstrated that this method outperformed existing approaches, achieving average daily returns exceeding 24%.

Author

andrew910309

Language

EN