Reinforcement learning with dynamic convex risk measures

We develop an approach for solving time‐consistent risk‐sensitive stochastic optimization problems using model‐free reinforcement learning (RL). Specifically, we assume agents assess the risk of a sequence of random variables using dynamic convex risk measures. We employ a time‐consistent dynamic pr...

Full description

Saved in:
Bibliographic Details
Published in:Mathematical finance Vol. 34; no. 2; pp. 557 - 587
Main Authors: Coache, Anthony, Jaimungal, Sebastian
Format: Journal Article
Language:English
Published: Oxford Blackwell Publishing Ltd 01.04.2024
Subjects:
Algorithms
Arbitrage
Dynamic programming
Flexibility
Hedging
Learning
Machine learning
Neural networks
Obstacle avoidance
Optimization
Policies
Random variables
Reinforcement
Risk
Risk assessment
Robot control
ISSN:0960-1627, 1467-9965
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We develop an approach for solving time‐consistent risk‐sensitive stochastic optimization problems using model‐free reinforcement learning (RL). Specifically, we assume agents assess the risk of a sequence of random variables using dynamic convex risk measures. We employ a time‐consistent dynamic programming principle to determine the value of a particular policy, and develop policy gradient update rules that aid in obtaining optimal policies. We further develop an actor–critic style algorithm using neural networks to optimize over policies. Finally, we demonstrate the performance and flexibility of our approach by applying it to three optimization problems: statistical arbitrage trading strategies, financial hedging, and obstacle avoidance robot control.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0960-1627
1467-9965
DOI:10.1111/mafi.12388