# Breaking the Cold-Start Barrier: Reinforcement Learning with Double and Dueling DQNs

## TL;DR

This paper introduces a reinforcement learning approach using Double and Dueling DQNs to improve recommendations for new users with limited data, outperforming traditional methods in accuracy and privacy preservation.

## Contribution

It presents a novel combination of advanced DQN variants with matrix factorization to address the cold-user problem in recommender systems.

## Key findings

- Dueling DQN significantly reduces RMSE for cold users.
- The proposed method outperforms traditional popularity-based and active learning strategies.
- The approach maintains high recommendation accuracy without using sensitive demographic data.

## Abstract

Recommender systems struggle to provide accurate suggestions to new users with limited interaction history, a challenge known as the cold-user problem. This paper proposes a reinforcement learning approach using Double and Dueling Deep Q-Networks (DQN) to dynamically learn user preferences from sparse feedback, enhancing recommendation accuracy without relying on sensitive demographic data. By integrating these advanced DQN variants with a matrix factorization model, we achieve superior performance on a large e-commerce dataset compared to traditional methods like popularity-based and active learning strategies. Experimental results show that our method, particularly Dueling DQN, reduces Root Mean Square Error (RMSE) for cold users, offering an effective solution for privacy-constrained environments.