# Option Hedging with Risk Averse Reinforcement Learning

arXiv: https://arxiv.org/abs/2010.12245 · HTML: https://mlsanity.com/paper/2010.12245/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2020.

## Built on by (most cited first, 13 of 13)

- [Efficient Risk-Averse Reinforcement Learning](https://mlsanity.com/paper/2205.05138/) (2022)
- [Reinforcement Learning for Quantitative Trading](https://mlsanity.com/paper/2109.13851/) (2021)
- [Deep Hedging: Continuous Reinforcement Learning for Hedging of General Portfolios across Multiple Risk Aversions](https://mlsanity.com/paper/2207.07467/) (2022)
- [The Evolution of Reinforcement Learning in Quantitative Finance: A Survey](https://mlsanity.com/paper/2408.10932/) (2024)
- [Hedging of Financial Derivative Contracts via Monte Carlo Tree Search](https://mlsanity.com/paper/2102.06274/) (2021)
- [Distributional Adversarial Attacks and Training in Deep Hedging](https://mlsanity.com/paper/2508.14757/) (2025)
- [Applications of Reinforcement Learning in Deregulated Power Market: A Comprehensive Review](https://mlsanity.com/paper/2205.08369/) (2022)
- [Reinforcement Learning for Credit Index Option Hedging](https://mlsanity.com/paper/2307.09844/) (2023)
- [EX-DRL: Hedging Against Heavy Losses with EXtreme Distributional Reinforcement Learning](https://mlsanity.com/paper/2408.12446/) (2024)
- [Risk-averse policies for natural gas futures trading using distributional reinforcement learning](https://mlsanity.com/paper/2501.04421/) (2025)
- [Revisiting Ensemble Methods for Stock Trading and Crypto Trading Tasks at ACM ICAIF FinRL Contest 2023-2024](https://mlsanity.com/paper/2501.10709/) (2025)
- [Adaptive Finite-Budget Training for CVaR Risk-Aware Q-Learning](https://mlsanity.com/paper/2608.04305/) (2026)
- [Eliciting ESG Preferences for Reinforcement Learning-Based Portfolio Optimization](https://mlsanity.com/paper/2609.02677/) (2026)

## Abstract (arXiv)

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.