Generative Sequential Notification Optimization via Multi-Objective Decision Transformers
On the map: Offline RL and imitation learning from data → Decision transformers and sequence modeling
Abstract (arXiv)
Notifications are an important communication channel for delivering timely and relevant information. Optimizing their delivery involves addressing complex sequential decision-making challenges under constraints such as message utility and user fatigue. Offline reinforcement learning (RL) methods, such as Conservative Q-Learning (CQL), have been applied to this problem but face practical challenges at scale, including instability, sensitivity to distribution shifts, limited reproducibility, and difficulties with explainability in high-dimensional recommendation settings. We present a Decision Transformer (DT) based framework that reframes policy learning as return-conditioned supervised learning, improving robustness, scalability, and modeling flexibility. Our contributions include a real-world comparison with CQL, a multi-reward design suitable for non-episodic tasks, a quantile regression approach to return-to-go conditioning, and a production-ready system with circular buffer-based sequence processing for near-real-time inference. Extensive offline and online experiments in a deployed notification system show that our approach improves notification utility and overall session activity while minimizing user fatigue. Compared to a multi-objective CQL-based agent, the DT-based approach achieved a +0.72% increase in sessions for notification decision-making at LinkedIn by making notification recommendation more relevant.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Decision transformers and sequence modeling, one of 13 directions in Offline RL and imitation learning from data. Builds on 14 of its 29 references that are in the map. First posted on arXiv 2 Sep 2025.
Builds on
14 of 29 references.
Closest ancestors · 4
Same direction, newest first
- 2024Planning Transformer: Long-Horizon Offline Reinforcement Learning with Planning Tokens14 Sep
- 2024Retentive Decision Transformer with Adaptive Masking for Reinforcement Learning based Recommendation Systems26 Mar
- 2021Offline Reinforcement Learning as One Big Sequence Modeling Problem3 Jun
- 2021Decision Transformer: Reinforcement Learning via Sequence Modeling2 Jun
Other references · 10
- 2017Attention Is All You Needcited by 60,361
- 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
- 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
- 2017End-to-end Driving via Conditional Imitation Learningcited by 485
- 2021RvS: What is Essential for Offline RL via Supervised Learning?cited by 185
- 2019Reward-Conditioned Policiescited by 102
- 2025Generative Auto-Bidding with Value-Guided Explorationscited by 23
- 2022Should I send this notification? Optimizing push notifications decision making by modeling the futurecited by 6
- 2022A State Transition Model for Mobile Notifications via Survival Analysiscited by 4
- 2024TIM: Temporal Interaction Model in Notification Systemcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2022Multi-objective Optimization of Notifications Using Offline Reinforcement Learning
- 2022Offline Reinforcement Learning for Mobile Notifications
- 2022Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL
- 2023When should we prefer Decision Transformers for Offline Reinforcement Learning?
- 2025A Comparison Between Decision Transformers and Traditional Offline Reinforcement Learning Algorithms
- 2025Reward Balancing Revisited: Enhancing Offline Reinforcement Learning for Recommender Systems
- 2023Robust Reinforcement Learning Objectives for Sequential Recommender Systems
- 2021Value Penalized Q-Learning for Recommender Systems