# Generative Optimization for Incentivized Advertising with Global Level Constraints

arXiv: https://arxiv.org/abs/2608.04421 · HTML: https://mlsanity.com/paper/2608.04421/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 48 references that are in the map.
- First posted on arXiv 5 Aug 2026.

## Builds on (most cited first, 30 of 35)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [Deep Recurrent Q-Learning for Partially Observable MDPs](https://mlsanity.com/paper/1507.06527/) (2015)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [Early Convolutions Help Transformers See Better](https://mlsanity.com/paper/2106.14881/) (2021)
- [Transformer Memory as a Differentiable Search Index](https://mlsanity.com/paper/2202.06991/) (2022)
- [Recommender Systems with Generative Retrieval](https://mlsanity.com/paper/2305.05065/) (2023)
- [OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment](https://mlsanity.com/paper/2502.18965/) (2025)
- [Do NLP Models Know Numbers? Probing Numeracy in Embeddings](https://mlsanity.com/paper/1909.07940/) (2019)
- [Deep Reinforcement Learning for Page-wise Recommendations](https://mlsanity.com/paper/1805.02343/) (2018)
- [TUTA: Tree-based Transformers for Generally Structured Table Pre-training](https://mlsanity.com/paper/2010.12537/) (2020)
- [Reinforcement Learning to Optimize Long-term User Engagement in Recommender Systems](https://mlsanity.com/paper/1902.05570/) (2019)
- [Budget Constrained Bidding by Model-free Reinforcement Learning in Display Advertising](https://mlsanity.com/paper/1802.08365/) (2018)
- [A Survey on Transformers in Reinforcement Learning](https://mlsanity.com/paper/2301.03044/) (2023)
- [Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction](https://mlsanity.com/paper/2203.10316/) (2022)
- [A Unified Framework for Marketing Budget Allocation](https://mlsanity.com/paper/1902.01128/) (2019)
- [Safe Offline Reinforcement Learning with Real-Time Budget Constraints](https://mlsanity.com/paper/2306.00603/) (2023)
- [E-Commerce Promotions Personalization via Online Multiple-Choice Knapsack with Uplift Modeling](https://mlsanity.com/paper/2108.13298/) (2021)
- [Free Lunch! Retrospective Uplift Modeling for Dynamic Promotions Recommendation within ROI Constraints](https://mlsanity.com/paper/2008.06293/) (2020)
- [LBCF: A Large-Scale Budget-Constrained Causal Forest Algorithm](https://mlsanity.com/paper/2201.12585/) (2022)
- [Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation](https://mlsanity.com/paper/2109.08331/) (2021)
- [Model-based Constrained MDP for Budget Allocation in Sequential Incentive Marketing](https://mlsanity.com/paper/2303.01049/) (2023)
- [Generative Regression Based Watch Time Prediction for Short-Video Recommendation](https://mlsanity.com/paper/2412.20211/) (2024)
- [Decision Focused Causal Learning for Direct Counterfactual Marketing Optimization](https://mlsanity.com/paper/2407.13664/) (2024)

## Abstract (arXiv)

Incentivized advertising allocates monetary or virtual rewards to drive user engagement, where a key challenge is optimizing continuous incentive magnitudes under strict global constraints. This problem is complicated by high-frequency interactions, delayed feedback, and non-Markovian user dynamics such as fatigue, which limit the effectiveness of existing uplift modeling and constrained reinforcement learning approaches. To address these challenges, we propose GOAL, a constraint-aware generative framework that formulates incentive allocation as a conditional sequence generation problem. GOAL directly generates incentive magnitudes conditioned on user histories and system-level global pressure, and integrates a hierarchical causal state encoder to capture both local behavioral dynamics and long-range dependencies. To enable flexible constraint control, we introduce Safe Constrained Policy Optimization (SCPO), which learns a single generative policy that generalizes across a spectrum of ROI constraints without retraining. Experiments on large-scale real-world data and a synthetic fatigue-aware environment show that GOAL improves long-term revenue and user retention while substantially reducing ROI violation rates compared to strong baselines.