Copertina

Action Chunking and Exploratory Data Collection Yield Exponential Improvements in Behavior Cloning for Continuous Control

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Thomas T., Pfrommer, Daniel, Pan, Chaoyi, Matni, Nikolai, Simchowitz, Max
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Systems and Control
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

The Pitfalls of Imitation Learning when Actions are Continuous
di: Simchowitz, Max, et al.
Pubblicazione: (2025)

A Test-Function Approach to Incremental Stability
di: Pfrommer, Daniel, et al.
Pubblicazione: (2025)

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

Single Trajectory Conformal Prediction
di: Lee, Brian, et al.
Pubblicazione: (2024)

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

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

On the Stability of Nonlinear Receding Horizon Control: A Geometric Perspective
di: Westenbroek, Tyler, et al.
Pubblicazione: (2021)

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

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

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

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

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

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

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

Scalable Distributed Nonlinear Control Under Flatness-Preserving Coupling
di: Yang, Fengjun, et al.
Pubblicazione: (2025)

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

Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error
di: Somalwar, Anne, et al.
Pubblicazione: (2025)

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

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

Density-Ratio Weighted Behavioral Cloning: Learning Control Policies from Corrupted Datasets
di: Pandian, Shriram Karpoora Sundara, et al.
Pubblicazione: (2025)

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

Towards a Theory of Control Architecture: A quantitative framework for layered multi-rate control
di: Matni, Nikolai, et al.
Pubblicazione: (2024)

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

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

Behavior Cloning of MPC for 3-DOF Robotic Manipulators
di: Guegan, Theo, et al.
Pubblicazione: (2026)

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

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

On the Sample Complexity of Imitation Learning for Smoothed Model Predictive Control
di: Pfrommer, Daniel, et al.
Pubblicazione: (2023)

Quad-LCD: Layered Control Decomposition Enables Actuator-Feasible Quadrotor Trajectory Planning
di: Srikanthan, Anusha, et al.
Pubblicazione: (2025)

Improved Sample Complexity of Imitation Learning for Barrier Model Predictive Control
di: Pfrommer, Daniel, et al.
Pubblicazione: (2024)

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

Reactive Temporal Logic-based Planning and Control for Interactive Robotic Tasks
di: Nawaz, Farhad, et al.
Pubblicazione: (2024)

Model-Based Diffusion for Trajectory Optimization
di: Pan, Chaoyi, et al.
Pubblicazione: (2024)

PyScrew: A Comprehensive Dataset Collection from Industrial Screw Driving Experiments
di: West, Nikolai, et al.
Pubblicazione: (2025)

Learning Complex Motion Plans using Neural ODEs with Safety and Stability Guarantees
di: Nawaz, Farhad, et al.
Pubblicazione: (2023)

Safe Planning in Interactive Environments via Iterative Policy Updates and Adversarially Robust Conformal Prediction
di: Mirzaeedodangeh, Omid, et al.
Pubblicazione: (2025)

Impact of Computation in Integral Reinforcement Learning for Continuous-Time Control
di: Cao, Wenhan, et al.
Pubblicazione: (2024)

Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior
di: Cui, Kai, et al.
Pubblicazione: (2023)

Exponential Stabilization of Linear Systems using Nearest-Action Control with Countable Input Set
di: Almuzakki, Muhammad Zaki, et al.
Pubblicazione: (2024)

Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking
di: Stolz, Roland, et al.
Pubblicazione: (2024)