Multi-Task Fusion via Reinforcement Learning for Long-Term User Satisfaction in Recommender Systems

TL;DR

This paper introduces a reinforcement learning-based framework for multi-task fusion in recommender systems, optimizing long-term user satisfaction through offline and online learning, and demonstrates its effectiveness on large-scale real-world data.

Contribution

It proposes a novel Batch RL approach for multi-task fusion in recommender systems, addressing long-term satisfaction and online exploration, with successful large-scale deployment.

Findings

Effective long-term user satisfaction optimization

Successful deployment on a large-scale industrial platform

Outperforms baseline models in real-world experiments

Abstract

Recommender System (RS) is an important online application that affects billions of users every day. The mainstream RS ranking framework is composed of two parts: a Multi-Task Learning model (MTL) that predicts various user feedback, i.e., clicks, likes, sharings, and a Multi-Task Fusion model (MTF) that combines the multi-task outputs into one final ranking score with respect to user satisfaction. There has not been much research on the fusion model while it has great impact on the final recommendation as the last crucial process of the ranking. To optimize long-term user satisfaction rather than obtain instant returns greedily, we formulate MTF task as Markov Decision Process (MDP) within a recommendation session and propose a Batch Reinforcement Learning (RL) based Multi-Task Fusion framework (BatchRL-MTF) that includes a Batch RL framework and an online exploration. The former exploits Batch RL to learn an optimal recommendation policy from the fixed batch data offline for long-term user satisfaction, while the latter explores potential high-value actions online to break through the local optimal dilemma. With a comprehensive investigation on user behaviors, we model the user satisfaction reward with subtle heuristics from two aspects of user stickiness and user activeness. Finally, we conduct extensive experiments on a billion-sample level real-world dataset to show the effectiveness of our model. We propose a conservative offline policy estimator (Conservative-OPEstimator) to test our model offline. Furthermore, we take online experiments in a real recommendation environment to compare performance of different models. As one of few Batch RL researches applied in MTF task successfully, our model has also been deployed on a large-scale industrial short video platform, serving hundreds of millions of users.