arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1808.00720cs.IRcs.LG
收藏

RecoGym:一个在线广告产品推荐问题的强化学习环境

RecoGym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertising

Criteo AI Labs(科韬人工智能实验室);Universitat Pompeu Fabra(庞培法布拉大学);Telefonica Research(西班牙电信研究院)

David Rohde, Stephen Bonner, Travis Dunlop, Flavian Vasile, Alexandros Karatzoglou

摘要:

推荐系统在许多环境中变得无处不在,并采取多种形式,从电子商务商店中的产品推荐,到搜索引擎中的查询建议,再到社交网络中的朋友推荐。目前的研究方向主要是基于从历史数据的监督学习,似乎显示出收益递减,许多从业者报告了监督学习的离线指标的改进与新提出的模型的在线性能之间的差异。一个可能的原因是,我们使用了错误的范式:当着眼于收集历史性能数据的长期周期时,创建推荐模型的新版本,A/B测试然后推出。我们看到,强化学习(RL)设置有很多共同点,其中智能体观察环境并对其采取行动,以便将其状态改变为更好的状态(具有更高奖励的状态)。为此,我们介绍了RIGYM,RL环境的建议,这是由用户的电子商务模式和用户响应的发布商网站上的建议模型定义的。我们相信,这是推荐系统研究领域向前迈出的重要一步,可以开辟推荐系统和强化学习社区之间的合作途径,并使离线和在线性能指标更好地保持一致。

英文摘要:

Recommender Systems are becoming ubiquitous in many settings and take many forms, from product recommendation in e-commerce stores, to query suggestions in search engines, to friend recommendation in social networks. Current research directions which are largely based upon supervised learning from historical data appear to be showing diminishing returns with a lot of practitioners report a discrepancy between improvements in offline metrics for supervised learning and the online performance of the newly proposed models. One possible reason is that we are using the wrong paradigm: when looking at the long-term cycle of collecting historical performance data, creating a new version of the recommendation model, A/B testing it and then rolling it out. We see that there a lot of commonalities with the reinforcement learning (RL) setup, where the agent observes the environment and acts upon it in order to change its state towards better states (states with higher rewards). To this end we introduce RecoGym, an RL environment for recommendation, which is defined by a model of user traffic patterns on e-commerce and the users response to recommendations on the publisher websites. We believe that this is an important step forward for the field of recommendation systems research, that could open up an avenue of collaboration between the recommender systems and reinforcement learning communities and lead to better alignment between offline and online performance metrics.

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。

↑