Deep Reinforcement Learning Framework for Diversified Portfolio Management Across Global Equity Markets

TL;DR

This paper presents a deep reinforcement learning framework for global equity portfolio management, evaluating various configurations and demonstrating benefits during uncertain market regimes.

Contribution

It introduces a novel RL-based approach with multiple model configurations, incorporating transaction costs and diversification, evaluated across diverse markets and time periods.

Findings

RL strategies show significant abnormal returns in Euro Stoxx 50.

No strategy achieves statistically significant excess returns across all markets.

Ensemble methods and diversification improve risk-adjusted performance.

Abstract

This study develops and evaluates a deep reinforcement learning framework for dynamic portfolio allocation across global equity markets. The Soft Actor-Critic algorithm is used to learn continuous portfolio weights within a Markov Decision Process, incorporating transaction costs, turnover penalties, and diversification constraints into the reward function. Five model configurations are compared, varying in reward formulation, policy structure (flat versus hierarchical Dirichlet), portfolio constraints, and temporal encoder (LSTM versus Transformer), and evaluated via walk-forward optimization across sixteen out-of-sample folds spanning 2003-2026 on the Nasdaq-100, Nikkei 225, and Euro Stoxx 50. Results show that RL strategies achieve competitive risk-adjusted performance primarily in the Euro Stoxx 50, where statistically significant abnormal returns are observed, but the central hypothesis is only partially confirmed: no strategy achieves statistically significant excess returns relative to Buy and Hold under HAC-robust inference across all markets. Regime analysis reveals that RL adds the most value during periods of elevated uncertainty, while ensemble aggregation across markets improves risk-adjusted performance and confirms the benefits of geographic diversification.