paper-with-me

홈 › Papers

On the Sample Complexity of Imitation Learning for Smoothed Model Predictive Control

2023-06-02 · Daniel Pfrommer, Swati Padmanabhan, Kwangjun Ahn, Jack Umenberger, Tobia Marcucci, Zakaria Mhammedi, Ali Jadbabaie

Recent work in imitation learning has shown that having an expert controller that is both suitably smooth and stable enables stronger guarantees on the performance of the learned controller. However, constructing such smoothed expert controllers for arbitrary systems remains challenging, especially in the presence of input and state constraints. As our primary contribution, we show how such a smoothed expert can be designed for a general class of systems using a log-barrier-based relaxation of a standard Model Predictive Control (MPC) optimization problem. At the crux of this theoretical guarantee on smoothness is a new lower bound we prove on the optimality gap of the analytic center associated with a convex Lipschitz function, which we hope could be of independent interest. We validate our theoretical findings via experiments, demonstrating the merits of our smoothing approach over randomized smoothing.

📄 PDF Abstract BibTeX arXiv:2306.01914

Code (0)

등록된 구현이 없습니다.

Tasks

Imitation LearningLearning TheoryModel Predictive Control

Similar Papers 제목 키워드 기반

Improved Sample Complexity of Imitation Learning for Barrier Model Predictive Control

2024-10-01 · Daniel Pfrommer, Swati Padmanabhan, Kwangjun Ahn, Jack Umenberger 외

Recent work in imitation learning has shown that having an expert controller that is both suitably smooth and stable enables stronger guarantees on the performance of the learned controller. However, constructing such sm…

Imitation LearningModel Predictive Control

Increasing Information for Model Predictive Control with Semi-Markov Decision Processes

2025-01-28 · Rémy Hosseinkhan Boucher, Onofrio Semeraro, Lionel Mathelin

Recent works in Learning-Based Model Predictive Control of dynamical systems show impressive sample complexity performances using criteria from Information Theory to accelerate the learning procedure. However, the sequen…

Model Predictive Control

Model Predictive Control via On-Policy Imitation Learning

2022-10-17 · Kwangjun Ahn, Zakaria Mhammedi, Horia Mania, Zhang-Wei Hong 외

In this paper, we leverage the rapid advances in imitation learning, a topic of intense recent focus in the Reinforcement Learning (RL) literature, to develop new sample complexity results and performance guarantees for …

Imitation LearningmodelModel Predictive ControlReinforcement Learning (RL)

Smoothed Score Queries and the Complexity of Sampling

2026-05-26 · Jingbo Liu arxiv

We study the query complexity of sampling from high-dimensional Gaussian distributions using gradient information. In the standard oracle model, exact gradients expose only matrix-vector products with the precision matri…

Model Predictive Adversarial Imitation Learning for Planning from Observation

2025-07-29 · Tyler Han, Yanda Bao, Bhaumik Mehta, Gabriel Guo 외 arxiv

Human demonstration data is often ambiguous and incomplete, motivating imitation learning approaches that also exhibit reliable planning behavior. A common paradigm to perform planning-from-demonstration involves learnin…

Reinforcement Learning