arXiv cs.AI· Wenwen Si, Honghao Wei·· 10 天前AI 评分22
RLCP：用校准剪枝的自适应动作集强化学习做序列推荐
Reinforcement Learning with Conformal Action Sets: An Application to Sequential Recommendation
AI 导读
针对序列推荐固定候选集大小的问题，研究者提出 RLCP（Reinforcement Learning with Calibrated Pruning），用 critic 分数和在线阈值自适应调整保留的动作集，并证明自适应轨迹上代理漏检率的确定性上界。
正文 · 原文
Abstract:Sequential recommenders typically use a fixed slate size even though the number of useful alternatives changes within a session. We propose Reinforcement Learning with Calibrated Pruning (RLCP), which adapts the retained action set using critic scores and an online threshold. The threshold is updated from binary feedback indicating whether the set contains an action in a proxy target. We prove a deterministic bound on the observed proxy miss rate along adaptive trajectories. To quantify the effect of pruning on reward, we derive an exact decomposition of value loss into filtering and selection losses. Under explicit proxy and critic approximation conditions, this decomposition yields a finite session reward bound that also accounts for imperfect selection and set truncation, without requiring the learning parameters to converge. Experiments on KuaiRand-Pure and MovieLens 1M compare two RLCP implementations with four RL baselines. In each of the 19 configurations, at least one RLCP variant achieves the highest catalog diversity, reaching $1.11\times$ to $5.21\times$ that of the strongest baseline, with competitive session depth and no larger retained sets.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.08743 [cs.LG] |
| (or arXiv:2610.08743v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08743 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wenwen Si [view email]
[v1]
Tue, 6 Oct 2026 17:40:52 UTC (861 KB)
来源：arXiv cs.AI · arxiv.org