Deep Hedging Under Market Frictions: A Comparison of DRL Models for Options Hedging with Impact and Transaction Costs
Bibliographic record
Abstract
This paper investigates the use of reinforcement learning (RL) algorithms to learn adaptive hedging strategies for derivatives under realistic market conditions, incorporating permanent market impact, execution slippage, and transaction costs. Market frictions arising from trading have been explored in the optimal trade execution literature; however, their influence on derivative hedging strategies remains comparatively understudied within RL contexts. Traditional hedging methods have typically assumed frictionless markets with only transaction costs. We illustrate that the dynamic decision problem posed by hedging with frictions can be modelled effectively with RL, demonstrating efficacy across various market frictions to minimize hedging losses. The results include a comparative analysis of the performance of three RL models across simulated price paths, demonstrating their varying effectiveness and adaptability in these friction-intensive environments. We find that RL agents, specifically TD3 and SAC, can outperform traditional delta hedging strategies in both simplistic and complex, illiquid environments highlighted by 2/3rd reductions in expected hedging losses and over 50% reductions in 5th percentile conditional value at risk (CVaR). These findings demonstrate that DRL agents can serve as a valuable risk management tool for financial institutions, especially given their adaptability to different market conditions and securities.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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 source (direct Gemma or distilled Codex), 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".