arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.13287cs.LGcs.IR
收藏

用于信息选择系统的Top-K排序深度上下文Bandits

Top-K Ranking Deep Contextual Bandits for Information Selection Systems

DEVCOM Army Research Laboratory(美国陆军研究实验室);University of Maryland(马里兰大学)

Jade Freeman, Michael Rawson

摘要:

在当今的技术环境中,信息是丰富的,动态的,和异构的性质。信息的自动过滤和优先级排序是基于信息是否为目标增加了实质性价值之间的区别。上下文多臂强盗已被广泛用于学习根据用户兴趣或相关性过滤内容和优先级。学习排名技术优化了项目的相关性排名,允许相应地选择内容。我们提出了一种新的方法,top-K排名的上下文多臂强盗框架下。我们用神经网络对随机奖励函数进行建模,以允许非线性近似来学习奖励和上下文之间的关系。我们展示了这种方法,并评估了在模拟场景中使用真实世界数据集从实验中学习的性能。实验结果表明,该方法在复杂的奖励结构和高维的上下文特征下表现良好。

英文摘要:

In today's technology environment, information is abundant, dynamic, and heterogeneous in nature. Automated filtering and prioritization of information is based on the distinction between whether the information adds substantial value toward one's goal or not. Contextual multi-armed bandit has been widely used for learning to filter contents and prioritize according to user interest or relevance. Learn-to-Rank technique optimizes the relevance ranking on items, allowing the contents to be selected accordingly. We propose a novel approach to top-K rankings under the contextual multi-armed bandit framework. We model the stochastic reward function with a neural network to allow non-linear approximation to learn the relationship between rewards and contexts. We demonstrate the approach and evaluate the the performance of learning from the experiments using real world data sets in simulated scenarios. Empirical results show that this approach performs well under the complexity of a reward structure and high dimensional contextual features.

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。

↑