Scholars release paper on catastrophic risk awareness in deep reinforcement learning
Get up to speed
Carlos Pérez Octavio Mendoza and Frédéric Godin published an academic paper on arXiv on October 21, 2026, proposing to extend the Extreme Value Theory (EVT) method for Conditional Value-at-Risk (CVaR) optimization to high-dimensional neural network policies. A differentiable tail risk objective is obtained through peak-over-threshold representation and moment estimation, allowing direct calculation of finite-sample gradients via automatic differentiation. In deep hedging problem tests involving rare extreme market fluctuations, EVT-trained policies exhibited lower hedging losses under extreme scenario evaluations. This method provides a feasible alternative for training neural network policies when observations related to extreme risks are scarce.
AI-generated from reports · 2 hr agoUpdated
Coverage timeline
Follow the coverage to understand different sides of the event.
- arXiv q-finCatastrophic Risk-Aware Methods in Deep Reinforcement Learning
This study extends the Extreme Value Theory (EVT) method for Conditional Value-at-Risk (CVaR) optimization to high-dimensional neural network policies. It obtains a differentiable tail risk objective through peak-over-threshold representation and moment estimation, allowing direct calculation of finite-sample gradients via automatic differentiation. In deep hedging problem tests involving rare extreme market fluctuations, EVT-trained strategies exhibit lower hedging losses under extreme scenario evaluation, providing a feasible alternative for training neural network policies when observations related to extreme risks are scarce.
Trend of this event
Not enough consecutive observations yet; trend is not drawn.