Simulation-Based Benchmarking of Reinforcement Learning Agents for Personalized Retail Promotions
This provides a practical framework for simulating AI agents in retail to optimize customer journeys, though it is incremental as it focuses on benchmarking existing methods.
The paper tackled the problem of sparse customer purchase events in retail by benchmarking reinforcement learning agents for personalized coupon targeting using comprehensive simulations, finding that contextual bandit and deep RL methods outperformed static policies.
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.