1 option
Statistical Limits and Efficient Algorithms for Learning-Enabled Control Bruce Donald Lee
- Format:
- Book
- Thesis/Dissertation
- Author/Creator:
- Lee, Bruce Donald, author.
- Language:
- English
- Subjects (All):
- Electrical engineering.
- Statistics.
- Computer science.
- 0544.
- 0984.
- 0800.
- 0463.
- Local Subjects:
- Electrical engineering.
- Statistics.
- Computer science.
- 0544.
- 0984.
- 0800.
- 0463.
- Genre:
- Academic theses
- Physical Description:
- 1 electronic resource (399 pages)
- Contained In:
- Dissertations Abstracts International 87-03B
- Place of Publication:
- Ann Arbor : ProQuest Dissertations and Theses, 2025
- Language Note:
- English
- Summary:
- As the use of large-scale learning for control continues to grow, the development of sample-efficient algorithms becomes increasingly critical. However, even in the simplest settings, we often do not know algorithms which achieve optimal sample complexity with respect to particular problem instances. This thesis discusses recent progress towards understanding sample efficient algorithms in learning-enabled control. First, we examine tradeoffs between performance and robustness by showing that robust control necessarily sacrifices performance in benign, non-adversarial settings. Next, we examine the problem of offline reinforcement learning over continuous state, action, and observation spaces. We present lower bounds highlighting instances of this problem that have a high sample complexity, regardless of the learning algorithm. We also consider efficient algorithms, and derive the first tight finite sample bounds on the excess cost of learning to control for a general class of nonlinear dynamical systems. Together, these bounds highlight the importance of the dataset, motivating our study of optimal task-oriented experiment design. Finally, we examine the use of large-scale learning for control, in which models trained to perform well on a variety of control tasks are fine-tuned to execute a new control task. We study this problem from the viewpoint of representation learning in the settings of imitation learning and adaptive control, achieving bounds on the imitation gap and regret, respectively
- Notes:
- Source: Dissertations Abstracts International, Volume: 87-03, Section: B.
- Advisors: Matni, Nikolai Committee members: Pappas, George J.; Morari, Manfred
- Ph.D. University of Pennsylvania 2025
- Local Notes:
- School code: 0175
- ISBN:
- 9798291596616
- Access Restriction:
- Restricted for use by site license
The Penn Libraries is committed to describing library materials using current, accurate, and responsible language. If you discover outdated or inaccurate language, please fill out this feedback form to report it and suggest alternative language.