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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Langming, Wang, Wanyu, Zhang, Chi, Li, Bo, Yin, Hongzhi, Wei, Xuetao, Su, Wenbo, Zheng, Bo, Zhao, Xiangyu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912472690065408
author Liu, Langming
Wang, Wanyu
Zhang, Chi
Li, Bo
Yin, Hongzhi
Wei, Xuetao
Su, Wenbo
Zheng, Bo
Zhao, Xiangyu
author_facet Liu, Langming
Wang, Wanyu
Zhang, Chi
Li, Bo
Yin, Hongzhi
Wei, Xuetao
Su, Wenbo
Zheng, Bo
Zhao, Xiangyu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_23090
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems
Liu, Langming
Wang, Wanyu
Zhang, Chi
Li, Bo
Yin, Hongzhi
Wei, Xuetao
Su, Wenbo
Zheng, Bo
Zhao, Xiangyu
Information Retrieval
Machine Learning
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.
title Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems
topic Information Retrieval
Machine Learning
url https://arxiv.org/abs/2506.23090