Optimizing Portfolio with Two-Sided Transactions and Lending: A Reinforcement Learning Framework

TL;DR

This paper introduces a reinforcement learning framework for portfolio management that effectively handles high-risk, volatile markets by incorporating two-sided transactions and lending, leading to improved risk-adjusted returns in cryptocurrency trading.

Contribution

The study develops a novel RL environment and reward function tailored for high-risk markets, integrating lending and two-sided transactions, and demonstrates its effectiveness in crypto portfolio management.

Findings

Outperforms benchmarks in high-volatility periods

Achieves higher return-to-risk ratios

Demonstrates robust profitability in volatile markets

Abstract

This study presents a Reinforcement Learning (RL)-based portfolio management model tailored for high-risk environments, addressing the limitations of traditional RL models and exploiting market opportunities through two-sided transactions and lending. Our approach integrates a new environmental formulation with a Profit and Loss (PnL)-based reward function, enhancing the RL agent's ability in downside risk management and capital optimization. We implemented the model using the Soft Actor-Critic (SAC) agent with a Convolutional Neural Network with Multi-Head Attention (CNN-MHA). This setup effectively manages a diversified 12-crypto asset portfolio in the Binance perpetual futures market, leveraging USDT for both granting and receiving loans and rebalancing every 4 hours, utilizing market data from the preceding 48 hours. Tested over two 16-month periods of varying market volatility, the model significantly outperformed benchmarks, particularly in high-volatility scenarios, achieving higher return-to-risk ratios and demonstrating robust profitability. These results confirm the model's effectiveness in leveraging market dynamics and managing risks in volatile environments like the cryptocurrency market.