Collaborative Research: CIF: Medium: Statistical and Algorithmic Foundations of Efficient Reinforcement Learning

合作研究：CIF：媒介：高效强化学习的统计和算法基础

• 批准号: 2106739
• 负责人: Yuxin Chen
• 金额: $ 40万
• 依托单位: Princeton University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-10-01 至 2022-03-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2106739&HistoricalAwards=false
• 关键词: Collaborative; Research; CIF; Medium; Statistical

As a data-driven paradigm for sequential decision making in unknown environments, Reinforcement Learning (RL) has received significant interest in recent years owing to its potential ability to solve difficult problems associated with future societal and scientific developments. However, the explosion of both model dimensionality and complexity in current and emerging applications exacerbates the challenge of achieving efficient RL in sample-starved situations, where data collection is expensive, time-consuming, or even high-stake, e.g., in clinical trials, online advertising, and autonomous systems. As a result, understanding and improving the sample and computational efficiencies of RL algorithms, sometimes under additional resource and system-level constraints, are rightly understood as critical to the successful deployment of RL in the future. In this project the PIs are involving students at all levels with diverse backgrounds in Electrical and Computer Engineering, and in Statistics, are developing education modules on RL to enrich the curriculum, and are co-organizing workshops and outreach activities to enable the broader dissemination of the project outcomes.Despite decades-long research efforts, the statistical and computational underpinnings of RL are still far from being well understood, especially when it comes to finite-sample and finite-time issues which are of crucial operational value. This research project is bridging the theory-practice gap of modern algorithmic approaches to RL. It is doing so by (i) characterizing fundamental limits for the sample and computations complexities in various RL settings, (ii) by developing performance guarantees and uncertainty quantification schemes, and (iii) by designing new computationally efficient algorithms that are provably near-optimal in terms of sample complexity in both single-agent and multi-agent settings. The expected outcomes will enable the trustworthy adoption of RL algorithms in sample-starved environments. The complementary expertise of the research team is being leveraged to enrich the statistical and algorithmic foundations of RL through model-, policy-, and value-based approaches. New efficient algorithms that rely on function approximation schemes are being developed in order to address the curse of dimensionality; the resulting techniques are intended to lead to non-asymptotic analysis tools that deal with the complicated statistical dependencies present in RL. This rich research agenda is expected to foster multidisciplinary efforts at the intersection of high-dimensional statistics, non-convex optimization, control theory, information theory, and machine learning.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.

作为在未知环境中进行连续决策的数据驱动范式，近年来，强化学习（RL）由于解决了与未来的社会和科学发展相关的困难问题，因此受到了浓厚的兴趣。但是，在当前和新兴应用程序中模型维度和复杂性的爆炸式爆炸加剧了在样品饥饿的情况下实现有效RL的挑战，在样品中，数据收集昂贵，耗时，甚至是高率，例如，在临床，在线广告和自主系统中。结果，理解和改善RL算法的样本和计算效率，有时在其他资源和系统级别的约束下，正确地理解为对未来RL成功部署至关重要。在这个项目中，PI在电气和计算机工程领域具有不同背景的各个级别的学生参与，并且在统计数据中，正在开发有关RL的教育模块，以丰富课程，并共同组织研讨会和外展活动，以使项目越来越广泛地构成范围，尤其是在整个研究工作中，始终是统计的，该研究范围是在统计的情况下，构成了计算的范围。有限样本和有限时间问题，具有至关重要的操作价值。该研究项目正在弥合RL的现代算法方法的理论实践差距。它是通过（i）表征各种RL设置中样本和计算复杂性的基本限制，（ii）通过开发性能保证和不确定性量化方案，以及（iii）通过设计新的计算有效算法，这些算法在单个基本和多元化设置中的样本复杂性方面非常优势，这些算法近乎最佳。预期的结果将使在样品饥饿的环境中值得信赖的RL算法采用。研究团队的互补专业知识正在利用通过模型，政策和基于价值的方法来丰富RL的统计和算法基础。为了解决维度的诅咒，正在开发依赖功能近似方案的新的有效算法。最终的技术旨在导致非吸收分析工具，以处理RL中存在的复杂统计依赖性。预计这一丰富的研究议程将在高维统计，非convex优化，控制理论，信息理论和机器学习的交集中促进多学科的努力。该奖项反映了NSF的法定任务，并被认为是值得通过基金会的知识分子优点和更广泛影响的审查审查的审查标准来通过评估来获得支持的。

项目成果

Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence

• DOI: 10.1137/21m1456789
• 发表时间: 2021-05
• 期刊: ArXiv
• 作者: Wenhao Zhan;Shicong Cen;Baihe Huang;Yuxin Chen;Jason D. Lee;Yuejie Chi

Tackling Small Eigen-Gaps: Fine-Grained Eigenvector Estimation and Inference Under Heteroscedastic Noise

• DOI: 10.1109/tit.2021.3111828
• 发表时间: 2021-11-01
• 期刊: IEEE TRANSACTIONS ON INFORMATION THEORY
• 影响因子: 2.5
• 作者: Cheng, Chen;Wei, Yuting;Chen, Yuxin
• 通讯作者: Chen, Yuxin

Softmax policy gradient methods can take exponential time to converge

• DOI: 10.1007/s10107-022-01920-6
• 发表时间: 2021-02
• 期刊: Mathematical Programming
• 影响因子: 2.7
• 作者: Gen Li;Yuting Wei;Yuejie Chi;Yuantao Gu;Yuxin Chen

Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction

• DOI: 10.1109/tit.2021.3120096
• 发表时间: 2020-06
• 期刊: IEEE Transactions on Information Theory
• 影响因子: 2.5
• 作者: Gen Li;Yuting Wei;Yuejie Chi;Yuantao Gu;Yuxin Chen

Breaking the sample complexity barrier to regret-optimal model-free reinforcement learning

打破样本复杂性障碍，实现后悔最优无模型强化学习

• DOI: 10.1093/imaiai/iaac034
• 发表时间: 2023
• 期刊: Information and Inference: A Journal of the IMA
• 作者: Li, Gen;Shi, Laixi;Chen, Yuxin;Chi, Yuejie
• 通讯作者: Chi, Yuejie