Breaking the Cold-Start Barrier: Reinforcement Learning with Double and Dueling DQNs
This addresses the challenge of providing accurate recommendations to new users with limited interaction history, particularly in privacy-constrained environments, though it appears incremental as it combines existing DQN variants with matrix factorization.
This paper tackles the cold-user problem in recommender systems by proposing a reinforcement learning approach using Double and Dueling DQNs integrated with matrix factorization, which reduces Root Mean Square Error (RMSE) for cold users on a large e-commerce dataset compared to traditional methods.
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.