Risk-Sensitive Deep Reinforcement Learning for Portfolio Optimization
Bibliographic record
Abstract
Navigating the complexity of petroleum futures markets—marked by extreme volatility, geopolitical uncertainty, and macroeconomic shocks—demands adaptive and risk-sensitive strategies. This paper explores an Adaptive Risk-sensitive Transformer-based Deep Reinforcement Learning (ART-DRL) framework to improve portfolio optimization in commodity futures trading. While deep reinforcement learning (DRL) has been applied in equities and forex, its use in commodities remains underexplored. We evaluate DRL models, including Deep Q-Networks (DQN), Proximal Policy Optimization (PPO), Advantage Actor-Critic (A2C), and Deep Deterministic Policy Gradient (DDPG), integrating dynamic reward functions and asset-specific optimization. Empirical results show improvements in risk-adjusted performance, with an annualized return of 1.353, a Sharpe Ratio of 4.340, and a Sortino Ratio of 57.766. Although the return is below DQN (1.476), the proposed model achieves better stability and risk control. Notably, the models demonstrate resilience by learning from historical periods of extreme volatility, including the COVID-19 pandemic (2020–2021) and geopolitical shocks such as the Russia–Ukraine conflict (2022), despite testing commencing in January 2023. This research offers a practical, data-driven framework for risk-sensitive decision-making in commodities, showing how machine learning can support portfolio management under volatile market conditions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".