Catastrophic-risk-aware reinforcement learning with extreme-value-theory-based policy gradients
By Parisa Davar, Frédéric Godin, Jose Garrido
Rating
1607
Battle Count: 216
Relevance
9/10
Highly relevant for risk management and option hedging in quantitative trading
Implementation Complexity
7/10
Requires understanding of extreme value theory and reinforcement learning
Reproducibility
4/5
Code available on GitHub, detailed methodology provided
About this paper
Methodology: POTPG (Peaks-Over-Threshold Policy Gradient). Problem types: Reinforcement Learning, Risk Management, Portfolio Optimization.
The interactive Everscope explorer (charts, battles, favorites) loads below.