Collaborative Research: CIF: Medium: Statistical and Algorithmic Foundations of Distributionally Robust Policy Learning

高效的数据驱动的政策学习和部署技术正在改变我们社会的许多方面，因为它们在工程、科学和社会应用中的广泛适用性。考虑到高性能计算的使用，例如，模拟器和数字双胞胎的使用已经成为测试和学习复杂优化策略的实用替代方案。因此，在过去的十年中，学术界对这一研究领域进行了大量的努力。然而，尽管取得了里程碑式的进展，这一领域的现有工作往往做出了一个关键的（隐含的）假设；也就是说，训练策略的环境将与部署策略的环境相同。在这个假设下学习的策略可能是脆弱的，因为这个假设通常在实际环境中不成立，这可能是由于模拟器模型规范或环境变化。该项目的目标是研究统计和算法基础，以便在未知环境中，在可能错误指定的生成模型下，开发可证明有效的鲁棒策略学习。该项目研究了上下文分组和强化学习（RL）环境中分布式稳健策略学习的综合统计和算法基础，并在广泛的非参数分布转移中开发了统计最佳和计算高效的算法。这些为捕获模型不可知的环境变化提供了一个强大的框架，但同时，由于未知的最坏环境位于无限维空间中，因此提出了智力挑战。提出的方案开辟了几个基本的研究方向，要求新颖和原则性的发展。首先，该项目开发了信息理论工具，以了解分布鲁棒性策略学习的基本学习限制，并描述分布不确定性如何导致学习困难。此外，该项目还开发了计算效率和统计最优估计方案，用于给定策略的分布鲁棒性性能分析。最后，该项目转化了由于学习分布式鲁棒策略而获得的估计效率增益。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

Efficient data-driven policy learning and deployment techniques are transforming many facets of our society as a result of their broad applicability in engineering, scientific and societal applications. Given the access to high-performance computing, the use of simulators and digital twins, for example, have emerged as practical alternatives to test and learn complex optimization policies. As a result, significant scholarly efforts have been devoted to this research area in the past decade. However, despite having made landmark progress, existing work in this area often makes a key (implicit) assumption; namely, that the environment in which the policy is trained will be the same as the environment in which the policy is deployed. Policies learned under this assumption can be fragile, as this assumption often does not hold in practical environments, either due to the simulator model specification or environment shifts. The goal of this project is to study statistical and algorithmic foundations for developing provably efficient robust policy learning in unknown environments, under a possibly misspecified generative model. The project studies comprehensive statistical and algorithmic foundations for distributionally robust policy learning in contextual bandits and reinforcement learning (RL) environments and develops statistically optimal and computationally efficient algorithms across a wide range of non-parametric distributional shifts. These provide a powerful framework for capturing model-agnostic environment changes, but at the same time, pose intellectual challenges as the unknown worst-case environment lies in an infinite-dimensional space. The presented program opens up several fundamental research directions that call for novel and principled developments. First, the project develops information-theoretic tools to understand the fundamental learning limits for distributionally robust policy learning and to characterize how the distributional uncertainty contributes to the difficulty of learning. Additionally, the project develops computationally efficient and statistically optimal estimation schemes for distributionally robust performance analysis of a given policy. Lastly, the project translates the efficiency gains in estimation due to learning a distributionally robust policy.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.