arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.07528cs.LGcs.IR
收藏

统一离策略学习排序:一种强化学习视角

Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective

University of Science and Technology of China(中国科学技术大学);Google DeepMind(谷歌DeepMind);Princeton University(普林斯顿大学);Penn State University(宾夕法尼亚州立大学);Oregon State University(俄勒冈州立大学)

Zeyu Zhang, Yi Su, Hui Yuan, Yiran Wu, Rishab Balasubramanian, Qingyun Wu, Huazheng Wang, Mengdi Wang

AI总结:

本文将排序过程统一建模为马尔可夫决策过程,提出点击模型无关的统一离策略学习排序方法CUOLR,利用离线强化学习在无需去偏和先验知识的情况下适应多种点击模型,并在大规模数据集上取得优于现有方法的鲁棒性能。

摘要:

离策略学习排序(LTR)旨在利用已部署的记录策略所收集的数据来优化排序器。然而,现有的离策略学习排序方法通常对用户如何产生点击数据(即点击模型)做出强假设,因此需要针对不同的点击模型专门定制其方法。在本文中,我们将一般随机点击模型下的排序过程统一建模为马尔可夫决策过程(MDP),并证明最优排序可以直接通过离线强化学习(RL)来学习。在此基础上,我们利用离线强化学习技术进行离策略学习排序,提出了点击模型无关的统一离策略学习排序(CUOLR)方法,该方法可以轻松应用于广泛的点击模型。通过对MDP的专门形式化构建,我们表明离线强化学习算法能够适应各种点击模型,而无需复杂的去偏技术和模型先验知识。在多个大规模数据集上的实验结果表明,CUOLR在不同点击模型下始终保持一致性和鲁棒性,同时持续优于最先进的离策略学习排序算法。

英文摘要:

Off-policy Learning to Rank (LTR) aims to optimize a ranker from data collected by a deployed logging policy. However, existing off-policy learning to rank methods often make strong assumptions about how users generate the click data, i.e., the click model, and hence need to tailor their methods specifically under different click models. In this paper, we unified the ranking process under general stochastic click models as a Markov Decision Process (MDP), and the optimal ranking could be learned with offline reinforcement learning (RL) directly. Building upon this, we leverage offline RL techniques for off-policy LTR and propose the Click Model-Agnostic Unified Off-policy Learning to Rank (CUOLR) method, which could be easily applied to a wide range of click models. Through a dedicated formulation of the MDP, we show that offline RL algorithms can adapt to various click models without complex debiasing techniques and prior knowledge of the model. Results on various large-scale datasets demonstrate that CUOLR consistently outperforms the state-of-the-art off-policy learning to rank algorithms while maintaining consistency and robustness under different click models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑