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 2006.08236cs.LGcs.AIstat.ML
收藏

非平稳非策略优化

Non-Stationary Off-Policy Optimization

Google Research(谷歌研究院)

Joey Hong, Branislav Kveton, Manzil Zaheer, Yinlam Chow, Amr Ahmed

摘要:

离策略学习是一个框架,用于根据另一个策略收集的数据,在不部署策略的情况下评估和优化策略。现实世界的环境通常是不稳定的,离线学习的策略应该适应这些变化。为了应对这一挑战,我们研究了分段固定上下文强盗的离线策略优化的新问题。我们提出的解决方案有两个阶段。在离线学习阶段,我们将记录的数据划分为分类的潜在状态,并为每个状态学习一个接近最优的子策略。在在线部署阶段,我们根据学习到的子策略的性能自适应地在它们之间切换。该方法具有实用性和可分析性,并在离线优化质量和在线部署过程中的遗憾方面提供了保证。为了证明我们方法的有效性,我们将其与合成和真实世界数据集上的最先进基线进行了比较。我们的方法优于仅对观察到的上下文起作用的方法。

英文摘要:

Off-policy learning is a framework for evaluating and optimizing policies without deploying them, from data collected by another policy. Real-world environments are typically non-stationary and the offline learned policies should adapt to these changes. To address this challenge, we study the novel problem of off-policy optimization in piecewise-stationary contextual bandits. Our proposed solution has two phases. In the offline learning phase, we partition logged data into categorical latent states and learn a near-optimal sub-policy for each state. In the online deployment phase, we adaptively switch between the learned sub-policies based on their performance. This approach is practical and analyzable, and we provide guarantees on both the quality of off-policy optimization and the regret during online deployment. To show the effectiveness of our approach, we compare it to state-of-the-art baselines on both synthetic and real-world datasets. Our approach outperforms methods that act only on observed context.

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。

↑