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.
Huang et al. (2025) studied this question.