Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems

Abstract

Online advertising in recommendation platforms has gained significant attention, with a predominant focus on channel recommendation and budget allocation strategies. However, current offline reinforcement learning (RL) methods face substantial challenges when applied to sparse advertising scenarios, primarily due to severe overestimation, distributional shifts, and overlooking budget constraints. To address these issues, we propose MTORL, a novel multi-task offline RL model that targets two key objectives. First, we establish a Markov Decision Process (MDP) framework specific to the nuances of advertising. Then, we develop a causal state encoder to capture dynamic user interests and temporal dependencies, facilitating offline RL through conditional sequence modeling. Causal attention mechanisms are introduced to enhance user sequence representations by identifying correlations among causal states. We employ multi-task learning to decode actions and rewards, simultaneously addressing channel recommendation and budget allocation. Notably, our framework includes an automated system for integrating these tasks into online advertising. Extensive experiments on offline and online environments demonstrate MTORL's superiority over state-of-the-art methods.

KDD 2025

References in corpus (16)

• A Brief Survey of Deep Reinforcement Learning
• Conservative Q-Learning for Offline Reinforcement Learning
• Deep Reinforcement Learning for Page-wise Recommendations
• Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning
• Towards Long-term Fairness in Recommendation
• LinRec: Linear Attention Mechanism for Long-term Sequential Recommender Systems
• Denoising Self-attentive Sequential Recommendation
• Jointly Learning to Recommend and Advertise
• HAMUR: Hyper Adapter for Multi-Domain Recommendation
• AutoDenoise: Automatic Data Instance Denoising for Recommendations
• Whole-Chain Recommendations
• Multi-Task Recommendations with Reinforcement Learning
• Predicting Different Types of Conversions with Multi-Task Learning in Online Advertising
• User Retention-oriented Recommendation with Decision Transformer
• Learning Multi-touch Conversion Attribution with Dual-attention Mechanisms for Online Advertising
• Modeling User Retention through Generative Flow Networks