Option Hedging with Risk Averse Reinforcement Learning
This work addresses the problem of efficient and robust option hedging for financial practitioners, offering a flexible method that adapts to varying risk preferences and market conditions, though it is incremental as it builds on existing risk-averse algorithms.
The paper tackled option hedging by applying a risk-averse reinforcement learning algorithm to a realistic environment with discrete time and transaction costs, resulting in a strategy that outperforms the Black & Scholes delta hedge in terms of volatility and profit/loss, with demonstrated robustness across different option characteristics and market behaviors.
In this paper we show how risk-averse reinforcement learning can be used to hedge options. We apply a state-of-the-art risk-averse algorithm: Trust Region Volatility Optimization (TRVO) to a vanilla option hedging environment, considering realistic factors such as discrete time and transaction costs. Realism makes the problem twofold: the agent must both minimize volatility and contain transaction costs, these tasks usually being in competition. We use the algorithm to train a sheaf of agents each characterized by a different risk aversion, so to be able to span an efficient frontier on the volatility-p\&l space. The results show that the derived hedging strategy not only outperforms the Black \& Scholes delta hedge, but is also extremely robust and flexible, as it can efficiently hedge options with different characteristics and work on markets with different behaviors than what was used in training.