Saved in:
Bibliographic Details
Main Authors: Lu, Liwei, Hu, Ruimeng, Yang, Xu, Zhu, Yi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.11967
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913779078397952
author Lu, Liwei
Hu, Ruimeng
Yang, Xu
Zhu, Yi
author_facet Lu, Liwei
Hu, Ruimeng
Yang, Xu
Zhu, Yi
contents This paper focuses on multi-agent stochastic differential games for jump-diffusion systems. On one hand, we study the multi-agent game for optimal investment in a jump-diffusion market. We derive constant Nash equilibria and provide sufficient conditions for their existence and uniqueness for exponential, power, and logarithmic utilities, respectively. On the other hand, we introduce a computational framework based on the actor-critic method in deep reinforcement learning to solve the stochastic control problem with jumps. We extend this algorithm to address the multi-agent game with jumps and utilize parallel computing to enhance computational efficiency. We present numerical examples of the Merton problem with jumps, linear quadratic regulators, and the optimal investment game under various settings to demonstrate the accuracy, efficiency, and robustness of the proposed method. In particular, neural network solutions numerically converge to the derived constant Nash equilibrium for the multi-agent game.
format Preprint
id arxiv_https___arxiv_org_abs_2404_11967
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Agent Relative Investment Games in a Jump Diffusion Market with Deep Reinforcement Learning Algorithm
Lu, Liwei
Hu, Ruimeng
Yang, Xu
Zhu, Yi
Optimization and Control
This paper focuses on multi-agent stochastic differential games for jump-diffusion systems. On one hand, we study the multi-agent game for optimal investment in a jump-diffusion market. We derive constant Nash equilibria and provide sufficient conditions for their existence and uniqueness for exponential, power, and logarithmic utilities, respectively. On the other hand, we introduce a computational framework based on the actor-critic method in deep reinforcement learning to solve the stochastic control problem with jumps. We extend this algorithm to address the multi-agent game with jumps and utilize parallel computing to enhance computational efficiency. We present numerical examples of the Merton problem with jumps, linear quadratic regulators, and the optimal investment game under various settings to demonstrate the accuracy, efficiency, and robustness of the proposed method. In particular, neural network solutions numerically converge to the derived constant Nash equilibrium for the multi-agent game.
title Multi-Agent Relative Investment Games in a Jump Diffusion Market with Deep Reinforcement Learning Algorithm
topic Optimization and Control
url https://arxiv.org/abs/2404.11967