Adaptive and Regime-Aware RL for Portfolio Optimization
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914044315697152 |
|---|---|
| author | Raj, Gabriel Nixon |
| author_facet | Raj, Gabriel Nixon |
| contents | This study proposes a regime-aware reinforcement learning framework for long-horizon portfolio optimization. Moving beyond traditional feedforward and GARCH-based models, we design realistic environments where agents dynamically reallocate capital in response to latent macroeconomic regime shifts. Agents receive hybrid observations and are trained using constrained reward functions that incorporate volatility penalties, capital resets, and tail-risk shocks. We benchmark multiple architectures, including PPO, LSTM-based PPO, and Transformer PPO, against classical baselines such as equal-weight and Sharpe-optimized portfolios. Our agents demonstrate robust performance under financial stress. While Transformer PPO achieves the highest risk-adjusted returns, LSTM variants offer a favorable trade-off between interpretability and training cost. The framework promotes regime-adaptive, explainable reinforcement learning for dynamic asset allocation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14385 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Adaptive and Regime-Aware RL for Portfolio Optimization Raj, Gabriel Nixon Portfolio Management Computational Finance This study proposes a regime-aware reinforcement learning framework for long-horizon portfolio optimization. Moving beyond traditional feedforward and GARCH-based models, we design realistic environments where agents dynamically reallocate capital in response to latent macroeconomic regime shifts. Agents receive hybrid observations and are trained using constrained reward functions that incorporate volatility penalties, capital resets, and tail-risk shocks. We benchmark multiple architectures, including PPO, LSTM-based PPO, and Transformer PPO, against classical baselines such as equal-weight and Sharpe-optimized portfolios. Our agents demonstrate robust performance under financial stress. While Transformer PPO achieves the highest risk-adjusted returns, LSTM variants offer a favorable trade-off between interpretability and training cost. The framework promotes regime-adaptive, explainable reinforcement learning for dynamic asset allocation. |
| title | Adaptive and Regime-Aware RL for Portfolio Optimization |
| topic | Portfolio Management Computational Finance |
| url | https://arxiv.org/abs/2509.14385 |