Aug 2026· Knowledge Discovery and Data Mining· pp. 7070-7081· 0 citations· 48 references
Computer Science
TL;DR
GOAL is a constraint-aware generative framework that formulates incentive allocation as a conditional sequence generation problem, and Safe Constrained Policy Optimization (SCPO), which learns a single generative policy that generalizes across a spectrum of ROI constraints without retraining.
Abstract
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.
This work introduces FARE (Fair Ranking Executor), a modular uncertainty-aware execution layer that translates any black-box CTR model's predictions into SOV-fair rankings without retraining the underlying model.
Arundeep Chinta, Lucas Vinh Tran, Jay Katukuri· arXiv.org· 0 citations
Adaptive rollout methods for group-relative reinforcement learning typically allocate a fixed per-update budget across prompts. We instead study how to coordinate a finite rollout budget over the entire training horizon. We formulate this problem using a concave surrogate utility of cumulative prompt exposure and intro...
Yi-Ming Zong, Yi-Ge Wang, Xin-Ting Hu et al.· 0 citations
Generative actors are transforming offline reinforcement learning (RL) by enabling expressive policy classes that model complex action distributions. However, this expressiveness also exposes a key challenge in heterogeneous datasets: generative policies can reproduce unreliable action modes whose return distributions...
This work proposes Effect-Marginal Policy Optimization (EMPO), which aligns policy optimization with execution-level equivalence through an effect-level surrogate that couples updates across alternative textual realizations, and shows that EMPO outperforms strong baselines in both task performance and learning efficien...
Shao-Jin Ma, Rui-Tao Wang, Peng-Yi Li et al.· 0 citations
Preference-based reward shaping can guide reinforcement learning, but adding preference signals to the reward may unintentionally change the task being optimized. We address this problem with IncentRL, a framework that introduces preference guidance while explicitly characterizing its effect on external-task performanc...
This work builds on the density-free kinetic-energy regularizer of FLAC, a recent reward-only method, and proposes Reparameterized Augmented-Lagrangian Flow Actor with Least Energy (RAFALE), an off-policy actor-critic method for safe RL.
Bo-Yan Li, Matthew Kim, Sylvia L. Herbert· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.