PPO-HRAP: Proximal Policy Optimization with a Hybrid Regime-Aware Policy for Risk-Controlled Trading

2026-10-01

AI Summary

This study addresses the inherent challenge in reinforcement learning-based trading of simultaneously capturing upside returns and controlling drawdowns by proposing the PPO-HRAP framework. This method integrates Proximal Policy Optimization (PPO) with volatility-aware, interpretable market mechanism priors, employing a hybrid action execution strategy to facilitate risk-controlled trading. Furthermore, a multi-objective reward function is designed to jointly optimize returns and risk. Experimental evaluations on the SPY dataset demonstrate that the proposed strategy achieves a Sharpe ratio of 0.64 while reducing the maximum drawdown to 18%, significantly outperforming the conventional buy-and-hold benchmark. These results establish PPO-HRAP as a novel paradigm for quantitative trading that effectively balances profitability with robustness.

Abstract

Reinforcement learning for trading often struggles to balance upside participation with drawdown control. Profit-only policies can collapse toward passive long exposure on upward-drifting assets, while aggressively risk-penalized rewards can become too defensive during volatile periods. This paper proposes PPO-HRAP, a hybrid regime-aware policy that combines Proximal Policy Optimization with an interpretable regime prior. The agent observes both market features and portfolio-state variables, receives a reward combining portfolio log return, VIX-conditioned drawdown-increase penalty, target-exposure deviation, and turnover cost, and executes a blended action between the PPO actor output and a regime-derived target exposure. On the held-out 2020-2022 SPY test window, PPO-HRAP achieves 27.62% total return, 8.48% annualized return, 0.6447 Sharpe ratio, 0.8588 Sortino ratio, and 0.4592 Calmar ratio, while reducing maximum drawdown from 34.10% for Buy and Hold to 18.47%. Across five SPY seeds, PPO-HRAP remains stable with mean total return $0.2725 \pm 0.0109$ and mean Sharpe ratio $0.6219 \pm 0.0565$. Single-run cross-asset tests on QQQ and DIA further show that the proposed method ranks first on total return and Sharpe ratio for all three reported assets. These results suggest that blending learned actions with a volatility-aware regime prior is a practical way to improve risk-adjusted trading behavior, although the current policy still incurs high turnover and cross-asset robustness beyond SPY remains limited to single-run evidence.

Problem

• Reinforcement Learning
• Risk-Controlled Trading
• Drawdown Control
• Regime-Aware Policy
• Portfolio Optimization

Innovation

• Proximal Policy Optimization
• Regime-Aware Policy
• Risk-Controlled Trading
• Reinforcement Learning
• Drawdown Penalty