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

2025/08/28 by Zhao, Minda
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Information Retrieval (cs.IR)

paper · doi:10.48550/arxiv.2508.21259

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.

Citations

• Choosing the Best of Both Worlds: Diverse and Novel Recommendations\n through Multi-Objective Reinforcement Learning
• Handling Cold-Start Collaborative Filtering with Reinforcement Learning
• Reinforcement Learning based Recommender System using Biclustering Technique
• Rainbow: Combining Improvements in Deep Reinforcement Learning
• Dueling Network Architectures for Deep Reinforcement Learning
• Deep Reinforcement Learning with Double Q-learning
• Playing Atari with Deep Reinforcement Learning
• Exploration in Interactive Personalized Music Recommendation: A Reinforcement Learning Approach
• Matrix Factorization Techniques for Recommender Systems

Related

• Handling Cold-Start Collaborative Filtering with Reinforcement Learning
• Sparsity Regularization For Cold-Start Recommendation
• Optimized Recommender Systems with Deep Reinforcement Learning
• Interactive Search Based on Deep Reinforcement Learning
• ColdGAN: Resolving Cold Start User Recommendation by using Generative Adversarial Networks