Simulation-Based Benchmarking of Reinforcement Learning Agents for Personalized Retail Promotions

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xia, Yu, Narayanamoorthy, Sriram, Zhou, Zhengyuan, Mabry, Joshua
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914799866085376
author Xia, Yu
Narayanamoorthy, Sriram
Zhou, Zhengyuan
Mabry, Joshua
author_facet Xia, Yu
Narayanamoorthy, Sriram
Zhou, Zhengyuan
Mabry, Joshua
contents The development of open benchmarking platforms could greatly accelerate the adoption of AI agents in retail. This paper presents comprehensive simulations of customer shopping behaviors for the purpose of benchmarking reinforcement learning (RL) agents that optimize coupon targeting. The difficulty of this learning problem is largely driven by the sparsity of customer purchase events. We trained agents using offline batch data comprising summarized customer purchase histories to help mitigate this effect. Our experiments revealed that contextual bandit and deep RL methods that are less prone to over-fitting the sparse reward distributions significantly outperform static policies. This study offers a practical framework for simulating AI agents that optimize the entire retail customer journey. It aims to inspire the further development of simulation tools for retail AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2405_10469
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Simulation-Based Benchmarking of Reinforcement Learning Agents for Personalized Retail Promotions
Xia, Yu
Narayanamoorthy, Sriram
Zhou, Zhengyuan
Mabry, Joshua
Artificial Intelligence
Machine Learning
Econometrics
The development of open benchmarking platforms could greatly accelerate the adoption of AI agents in retail. This paper presents comprehensive simulations of customer shopping behaviors for the purpose of benchmarking reinforcement learning (RL) agents that optimize coupon targeting. The difficulty of this learning problem is largely driven by the sparsity of customer purchase events. We trained agents using offline batch data comprising summarized customer purchase histories to help mitigate this effect. Our experiments revealed that contextual bandit and deep RL methods that are less prone to over-fitting the sparse reward distributions significantly outperform static policies. This study offers a practical framework for simulating AI agents that optimize the entire retail customer journey. It aims to inspire the further development of simulation tools for retail AI systems.
title Simulation-Based Benchmarking of Reinforcement Learning Agents for Personalized Retail Promotions
topic Artificial Intelligence
Machine Learning
Econometrics
url https://arxiv.org/abs/2405.10469