arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1502.02259stat.MLcs.LG
收藏

上下文马尔可夫决策过程

Contextual Markov Decision Processes

The Technion(以色列理工学院);Yahoo Labs(雅虎实验室)

Assaf Hallak, Dotan Di Castro, Shie Mannor

摘要:

我们考虑一个规划问题的动态和奖励的环境依赖于一个隐藏的静态参数称为上下文。我们的目标是学习一种策略,在所有情况下最大化累积的奖励。新的模型,称为上下文马尔可夫决策过程(CMDP),可以模拟客户的行为时,与网站(学习者)。客户的行为取决于性别,年龄,位置,设备等,基于该行为,网站的目标是确定客户特征,并优化他们之间的互动。我们的工作集中在一个基本的场景-有限的地平线与一个小的已知数量的可能的背景。我们提出了一个家庭的算法与可证明的保证,学习的基础模型和潜在的上下文,并优化CMDPs。边界获得具体的天真的实现,并讨论了框架的扩展,为今后的研究奠定了基础。

英文摘要:

We consider a planning problem where the dynamics and rewards of the environment depend on a hidden static parameter referred to as the context. The objective is to learn a strategy that maximizes the accumulated reward across all contexts. The new model, called Contextual Markov Decision Process (CMDP), can model a customer's behavior when interacting with a website (the learner). The customer's behavior depends on gender, age, location, device, etc. Based on that behavior, the website objective is to determine customer characteristics, and to optimize the interaction between them. Our work focuses on one basic scenario--finite horizon with a small known number of possible contexts. We suggest a family of algorithms with provable guarantees that learn the underlying models and the latent contexts, and optimize the CMDPs. Bounds are obtained for specific naive implementations, and extensions of the framework are discussed, laying the ground for future research.

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。

↑