Distributional Reinforcement Learning on Path-dependent Options
By: Ahmet Umur Özsoy
Potential Business Impact:
Prices risky financial bets more accurately.
We reinterpret and propose a framework for pricing path-dependent financial derivatives by estimating the full distribution of payoffs using Distributional Reinforcement Learning (DistRL). Unlike traditional methods that focus on expected option value, our approach models the entire conditional distribution of payoffs, allowing for risk-aware pricing, tail-risk estimation, and enhanced uncertainty quantification. We demonstrate the efficacy of this method on Asian options, using quantile-based value function approximators.
Similar Papers
Distributional Inverse Reinforcement Learning
Machine Learning (CS)
Learns how to do things by watching experts.
A Risk Sensitive Contract-unified Reinforcement Learning Approach for Option Hedging
Risk Management
Protects option sellers from big money losses.
Data-driven Option Pricing
Pricing of Securities
Helps predict stock option prices using past stock data.