Distributional Reinforcement Learning on Path-dependent Options

TL;DR

This paper introduces a distributional reinforcement learning framework for pricing path-dependent financial derivatives, enabling risk-aware valuation and tail-risk estimation by modeling the full payoff distribution rather than just expected values.

Contribution

It presents a novel approach that applies distributional reinforcement learning to derivative pricing, capturing the entire payoff distribution for improved risk management.

Findings

Effective modeling of payoff distributions for Asian options.

Enhanced risk and tail-risk estimation capabilities.

Demonstrated superiority over traditional expected-value methods.

Abstract

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.