SAMP-HDRL: Segmented Allocation with Momentum-Adjusted Utility for Multi-agent Portfolio Management via Hierarchical Deep Reinforcement Learning

TL;DR

SAMP-HDRL introduces a hierarchical deep reinforcement learning framework that dynamically segments assets, coordinates global and local decisions, and incorporates utility-based capital allocation to enhance multi-agent portfolio management in volatile markets.

Contribution

The paper presents a novel hierarchical DRL approach with dynamic asset grouping and utility-based capital allocation, improving robustness and interpretability in non-stationary market conditions.

Findings

Outperforms nine traditional and nine DRL benchmarks in volatile markets.

Achieves at least 5% higher Return, Sharpe, and Sortino ratios compared to the best baseline.

Demonstrates robustness through ablation studies and provides interpretability via SHAP analysis.

Abstract

Portfolio optimization in non-stationary markets is challenging due to regime shifts, dynamic correlations, and the limited interpretability of deep reinforcement learning (DRL) policies. We propose a Segmented Allocation with Momentum-Adjusted Utility for Multi-agent Portfolio Management via Hierarchical Deep Reinforcement Learning (SAMP-HDRL). The framework first applies dynamic asset grouping to partition the market into high-quality and ordinary subsets. An upper-level agent extracts global market signals, while lower-level agents perform intra-group allocation under mask constraints. A utility-based capital allocation mechanism integrates risky and risk-free assets, ensuring coherent coordination between global and local decisions. backtests across three market regimes (2019--2021) demonstrate that SAMP-HDRL consistently outperforms nine traditional baselines and nine DRL benchmarks under volatile and oscillating conditions. Compared with the strongest baseline, our method achieves at least 5\% higher Return, 5\% higher Sharpe ratio, 5\% higher Sortino ratio, and 2\% higher Omega ratio, with substantially larger gains observed in turbulent markets. Ablation studies confirm that upper--lower coordination, dynamic clustering, and capital allocation are indispensable to robustness. SHAP-based interpretability further reveals a complementary ``diversified + concentrated'' mechanism across agents, providing transparent insights into decision-making. Overall, SAMP-HDRL embeds structural market constraints directly into the DRL pipeline, offering improved adaptability, robustness, and interpretability in complex financial environments.