When Collaborative Filtering Meets Reinforcement Learning
This work addresses the challenge of sequential recommendations in online platforms, offering a domain-specific solution that is incremental by combining existing techniques.
The paper tackles the multi-step interactive recommendation problem by developing CFRL, a novel approach that integrates collaborative filtering and reinforcement learning to model user interactions as a Markov decision process and encode user states into a shared latent space, achieving improved performance on real-world datasets.
In this paper, we study a multi-step interactive recommendation problem, where the item recommended at current step may affect the quality of future recommendations. To address the problem, we develop a novel and effective approach, named CFRL, which seamlessly integrates the ideas of both collaborative filtering (CF) and reinforcement learning (RL). More specifically, we first model the recommender-user interactive recommendation problem as an agent-environment RL task, which is mathematically described by a Markov decision process (MDP). Further, to achieve collaborative recommendations for the entire user community, we propose a novel CF-based MDP by encoding the states of all users into a shared latent vector space. Finally, we propose an effective Q-network learning method to learn the agent's optimal policy based on the CF-based MDP. The capability of CFRL is demonstrated by comparing its performance against a variety of existing methods on real-world datasets.