Copertina

Foundations of Safe Online Reinforcement Learning in the Linear Quadratic Regulator: $\sqrt{T}$-Regret

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Schiffer, Benjamin, Janson, Lucas
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

Foundations of Safe Online Reinforcement Learning in the Linear Quadratic Regulator: Generalized Baselines
di: Schiffer, Benjamin, et al.
Pubblicazione: (2024)

Learning Decentralized Linear Quadratic Regulators with $\sqrt{T}$ Regret
di: Ye, Lintao, et al.
Pubblicazione: (2022)

Approximate Thompson Sampling for Learning Linear Quadratic Regulators with $O(\sqrt{T})$ Regret
di: Kim, Yeoneung, et al.
Pubblicazione: (2024)

Sample Complexity of the Linear Quadratic Regulator: A Reinforcement Learning Lens
di: Moghaddam, Amirreza Neshaei, et al.
Pubblicazione: (2024)

Sublinear Regret for a Class of Continuous-Time Linear-Quadratic Reinforcement Learning Problems
di: Huang, Yilie, et al.
Pubblicazione: (2024)

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

Scalar Federated Learning for Linear Quadratic Regulator
di: Rostami, Mohammadreza, et al.
Pubblicazione: (2026)

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

Any-Time Regret-Guaranteed Algorithm for Control of Linear Quadratic Systems
di: Chekan, Jafar Abbaszadeh, et al.
Pubblicazione: (2024)

Rate-Optimal Regret for the Safe Learning-based Control of the Constrained Linear Quadratic Regulator
di: Hutchinson, Spencer, et al.
Pubblicazione: (2026)

Almost Surely $\sqrt{T}$ Regret for Adaptive LQR
di: Lu, Yiwen, et al.
Pubblicazione: (2023)

Tsallis Entropy Regularization for Linearly Solvable MDP and Linear Quadratic Regulator
di: Hashizume, Yota, et al.
Pubblicazione: (2024)

Model-Free Learning for the Linear Quadratic Regulator over Rate-Limited Channels
di: Ye, Lintao, et al.
Pubblicazione: (2024)

Near-Optimal Distributed Linear-Quadratic Regulator for Networked Systems
di: Shin, Sungho, et al.
Pubblicazione: (2022)

Sample Complexity of Linear Quadratic Regulator Without Initial Stability
di: Moghaddam, Amirreza Neshaei, et al.
Pubblicazione: (2025)

Regret Analysis of Policy Optimization over Submanifolds for Linearly Constrained Online LQG
di: Chang, Ting-Jui, et al.
Pubblicazione: (2024)

Risk-Sensitive Soft Actor-Critic for Robust Deep Reinforcement Learning under Distribution Shifts
di: Enders, Tobias, et al.
Pubblicazione: (2024)

Model-Agnostic Zeroth-Order Policy Optimization for Meta-Learning of Ergodic Linear Quadratic Regulators
di: Pan, Yunian, et al.
Pubblicazione: (2024)

Risk-Aware Safe Reinforcement Learning for Control of Stochastic Linear Systems
di: Esmaeili, Babak, et al.
Pubblicazione: (2025)

Regret Bounds for Episodic Risk-Sensitive Linear Quadratic Regulator
di: Xu, Wenhao, et al.
Pubblicazione: (2024)

Online Reinforcement Learning in Markov Decision Process Using Linear Programming
di: Leon, Vincent, et al.
Pubblicazione: (2023)

Safe Online Control-Informed Learning
di: Zhou, Tianyu, et al.
Pubblicazione: (2025)

Global Rewards in Multi-Agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems
di: Hoppe, Heiko, et al.
Pubblicazione: (2023)

Online Linear Quadratic Tracking with Regret Guarantees
di: Karapetyan, Aren, et al.
Pubblicazione: (2023)

Online Nonstochastic Prediction: Logarithmic Regret via Predictive Online Least Squares
di: Pai, Chih-Fan, et al.
Pubblicazione: (2026)

Beyond $\mathcal{O}(\sqrt{T})$ Regret: Decoupling Learning and Decision-making in Online Linear Programming
di: Gao, Wenzhi, et al.
Pubblicazione: (2025)

Feasible Policy Iteration for Safe Reinforcement Learning
di: Yang, Yujie, et al.
Pubblicazione: (2023)

Safe and Robust Reinforcement Learning: Principles and Practice
di: Yamagata, Taku, et al.
Pubblicazione: (2024)

LexiSafe: Offline Safe Reinforcement Learning with Lexicographic Safety-Reward Hierarchy
di: Yang, Hsin-Jung, et al.
Pubblicazione: (2026)

Steady-State Error Compensation for Reinforcement Learning with Quadratic Rewards
di: Wang, Liyao, et al.
Pubblicazione: (2024)

Safe and Near-Optimal Control with Online Dynamics Learning
di: Prajapat, Manish, et al.
Pubblicazione: (2025)

Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part I
di: Tian, Yi, et al.
Pubblicazione: (2022)

Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part II
di: Tian, Yi, et al.
Pubblicazione: (2026)

Data-Driven Exploration for a Class of Continuous-Time Indefinite Linear--Quadratic Reinforcement Learning Problems
di: Huang, Yilie, et al.
Pubblicazione: (2025)

Kernel-Based Safe Exploration in Deep Reinforcement Learning
di: Majumdar, Rupak, et al.
Pubblicazione: (2026)

On the Foundation of Distributionally Robust Reinforcement Learning
di: Wang, Shengbo, et al.
Pubblicazione: (2023)

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

Safe Reinforcement Learning with Minimal Supervision
di: Quessy, Alexander, et al.
Pubblicazione: (2025)

Recursively Feasible Probabilistic Safe Online Learning with Control Barrier Functions
di: Castañeda, Fernando, et al.
Pubblicazione: (2022)

Lipschitz-Based Robustness Certification for Recurrent Neural Networks via Convex Relaxation
di: Hamelbeck, Paul, et al.
Pubblicazione: (2025)