Cover Image

Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Somalwar, Anne, Lee, Bruce D., Pappas, George J., Matni, Nikolai
Format:	Preprint
Published:	2025
Subjects:	Systems and Control Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Statistical Efficiency of Single- and Multi-step Models for Forecasting and Control
by: Somalwar, Anne, et al.
Published: (2026)

Active Learning for Control-Oriented Identification of Nonlinear Systems
by: Lee, Bruce D., et al.
Published: (2024)

Policy Gradient for LQR with Domain Randomization
by: Fujinami, Tesshu, et al.
Published: (2025)

Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer Samples
by: Zhang, Thomas T., et al.
Published: (2024)

State space models, emergence, and ergodicity: How many parameters are needed for stable predictions?
by: Ziemann, Ingvar, et al.
Published: (2024)

Single Trajectory Conformal Prediction
by: Lee, Brian, et al.
Published: (2024)

A Tutorial on the Non-Asymptotic Theory of System Identification
by: Ziemann, Ingvar, et al.
Published: (2023)

Nonasymptotic Regret Analysis of Adaptive Linear Quadratic Control with Model Misspecification
by: Lee, Bruce D., et al.
Published: (2023)

Regret Analysis of Multi-task Representation Learning for Linear-Quadratic Adaptive Control
by: Lee, Bruce D., et al.
Published: (2024)

Coordinating Planning and Tracking in Layered Control Policies via Actor-Critic Learning
by: Yang, Fengjun, et al.
Published: (2024)

Domain Randomization is Sample Efficient for Linear Quadratic Control
by: Fujinami, Tesshu, et al.
Published: (2025)

Rate-Optimal Non-Asymptotics for the Quadratic Prediction Error Method
by: Stamouli, Charis, et al.
Published: (2024)

Temporal Difference Learning with Compressed Updates: Error-Feedback meets Reinforcement Learning
by: Mitra, Aritra, et al.
Published: (2023)

Why Change Your Controller When You Can Change Your Planner: Drag-Aware Trajectory Generation for Quadrotor Systems
by: Zhang, Hanli, et al.
Published: (2024)

Conformal Prediction Regions for Time Series using Linear Complementarity Programming
by: Cleaveland, Matthew, et al.
Published: (2023)

Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Data
by: Zhang, Thomas T. C. K., et al.
Published: (2023)

Recursively Feasible Shrinking-Horizon MPC in Dynamic Environments with Conformal Prediction Guarantees
by: Stamouli, Charis, et al.
Published: (2024)

Learning Robust Output Control Barrier Functions from Safe Expert Demonstrations
by: Lindemann, Lars, et al.
Published: (2021)

Multi-Modal Conformal Prediction Regions with Simple Structures by Optimizing Convex Shape Templates
by: Tumu, Renukanandan, et al.
Published: (2023)

Flying Quadrotors in Tight Formations using Learning-based Model Predictive Control
by: Chee, Kong Yao, et al.
Published: (2024)

Adversarial Robustness of Deep State Space Models for Forecasting
by: Anand, Sribalaji C., et al.
Published: (2026)

Action Chunking and Exploratory Data Collection Yield Exponential Improvements in Behavior Cloning for Continuous Control
by: Zhang, Thomas T., et al.
Published: (2025)

eCP: Equivariant Conformal Prediction with pre-trained models
by: Bousias, Nikolaos, et al.
Published: (2026)

Distributionally Robust Imitation Learning: Layered Control Architecture for Certifiable Autonomy
by: Gahlawat, Aditya, et al.
Published: (2025)

Logarithmic Regret and Polynomial Scaling in Online Multi-step-ahead Prediction
by: Qian, Jiachen, et al.
Published: (2025)

Learning Local Control Barrier Functions for Hybrid Systems
by: Yang, Shuo, et al.
Published: (2024)

The Fragility of Learning LQG Controllers
by: Lee, Bruce D., et al.
Published: (2026)

Closed-loop Analysis of ADMM-based Suboptimal Linear Model Predictive Control
by: Srikanthan, Anusha, et al.
Published: (2024)

Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss
by: Ziemann, Ingvar, et al.
Published: (2024)

A Quantitative Framework for Navigating Controller Design Tradeoffs under Computational Constraints
by: Verhoek, Chris, et al.
Published: (2026)

Model approximation in MDPs with unbounded per-step cost
by: Bozkurt, Berk, et al.
Published: (2024)

DASA: Delay-Adaptive Multi-Agent Stochastic Approximation
by: Fabbro, Nicolò Dal, et al.
Published: (2024)

Learning Flatness-Preserving Residuals for Pure-Feedback Systems
by: Yang, Fengjun, et al.
Published: (2025)

Verification of Sequential Convex Programming for Parametric Non-convex Optimization
by: Sambharya, Rajiv, et al.
Published: (2025)

Filtering Jump Markov Systems with Partially Known Dynamics: A Model-Based Deep Learning Approach
by: Stamatelis, George, et al.
Published: (2025)

A Data-Driven Pool Strategy for Price-Makers Under Imperfect Information
by: Zheng, Kedi, et al.
Published: (2024)

Modular Distributed Nonconvex Learning with Error Feedback
by: Carnevale, Guido, et al.
Published: (2025)

Comparative Field Deployment of Reinforcement Learning and Model Predictive Control for Residential HVAC
by: Mulayim, Ozan Baris, et al.
Published: (2025)

On Globally Optimal Stochastic Policy Gradient Methods for Domain Randomized LQR Synthesis
by: Nguyen-Le, Alex, et al.
Published: (2026)

Federated Learning Approach to Mitigate Water Wastage
by: Ahmadi, Sina Hajer, et al.
Published: (2024)