Search papers, labs, and topics across Lattice.
This paper introduces GOAL, a generative framework that optimizes incentive allocation for advertising by treating it as a conditional sequence generation problem, addressing the complexities of high-frequency interactions and non-Markovian user dynamics. By integrating a hierarchical causal state encoder and the Safe Constrained Policy Optimization (SCPO) method, GOAL generates incentive magnitudes based on user histories while adhering to global constraints. Experiments demonstrate that GOAL significantly enhances long-term revenue and user retention, while also minimizing ROI violations compared to existing methods.
GOAL not only optimizes advertising incentives but also adapts seamlessly to varying ROI constraints without the need for retraining, revolutionizing how we approach incentivized user engagement.
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 \textbf{S}afe \textbf{C}onstrained \textbf{P}olicy \textbf{O}ptimization (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.
