Copertina

Bellman Residual Minimization for Control: Geometry, Stationarity, and Convergence

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lee, Donghwan, Yang, Hyukjun
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Systems and Control
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Contraction-Aligned Analysis of Soft Bellman Residual Minimization with Weighted Lp-Norm for Markov Decision Problem
di: Yang, Hyukjun, et al.
Pubblicazione: (2026)

Beyond the Bellman Fixed Point: Geometry and Fast Policy Identification in Value Iteration
di: Lee, Donghwan
Pubblicazione: (2026)

Analysis of Off-Policy Multi-Step TD-Learning with Linear Function Approximation
di: Lee, Donghwan
Pubblicazione: (2024)

Lyapunov-Certified Direct Switching Theory for Q-Learning
di: Lee, Donghwan
Pubblicazione: (2026)

Finite-Time Analysis of Q-Value Iteration for General-Sum Stackelberg Games
di: Jeong, Narim, et al.
Pubblicazione: (2026)

Finite-Time Analysis of Simultaneous Double Q-learning
di: Na, Hyunjun, et al.
Pubblicazione: (2024)

Finite-Time Accuracy of Temporal-Difference Learning Under Schur-Stable Recursions
di: Lee, Donghwan, et al.
Pubblicazione: (2022)

Deep Q-Learning with Gradient Target Tracking
di: Park, Bum Geun, et al.
Pubblicazione: (2025)

Verifiable Error Bounds for Physics-Informed Neural Network Solutions of Lyapunov and Hamilton-Jacobi-Bellman Equations
di: Liu, Jun
Pubblicazione: (2026)

Signatures Meet Dynamic Programming: Generalizing Bellman Equations for Trajectory Following
di: Ohnishi, Motoya, et al.
Pubblicazione: (2023)

Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics
di: Wu, Runzhe, et al.
Pubblicazione: (2024)

Universal Approximation Power of Deep Residual Neural Networks via Nonlinear Control Theory
di: Tabuada, Paulo, et al.
Pubblicazione: (2020)

Periodic Regularized Q-Learning
di: Yang, Hyukjun, et al.
Pubblicazione: (2026)

Residual Power Flow for Neural Solvers
di: Stiasny, Jochen, et al.
Pubblicazione: (2026)

Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods
di: Klein, Sara, et al.
Pubblicazione: (2023)

ORN-CBF: Learning Observation-conditioned Residual Neural Control Barrier Functions via Hypernetworks
di: Derajić, Bojan, et al.
Pubblicazione: (2025)

Online Residual Learning from Offline Experts for Pedestrian Tracking
di: Vlachos, Anastasios, et al.
Pubblicazione: (2024)

On the Convergence of Overlapping Schwarz Decomposition for Nonlinear Optimal Control
di: Na, Sen, et al.
Pubblicazione: (2020)

On Some Geometric Behavior of Value Iteration on the Orthant: Switching System Perspective
di: Lee, Donghwan
Pubblicazione: (2023)

Convergence and stability of Q-learning in Hierarchical Reinforcement Learning
di: Manenti, Massimiliano, et al.
Pubblicazione: (2025)

Geometry-Preserving Neural Architectures on Manifolds with Boundary
di: Elamvazhuthi, Karthik, et al.
Pubblicazione: (2026)

Enhancing Convergence of Decentralized Gradient Tracking under the KL Property
di: Chen, Xiaokai, et al.
Pubblicazione: (2024)

Is Bellman Equation Enough for Learning Control?
di: You, Haoxiang, et al.
Pubblicazione: (2025)

ControlSynth Neural ODEs: Modeling Dynamical Systems with Guaranteed Convergence
di: Mei, Wenjie, et al.
Pubblicazione: (2024)

A Short and Unified Convergence Analysis of the SAG, SAGA, and IAG Algorithms
di: Zhu, Feng, et al.
Pubblicazione: (2026)

On Linear Convergence of PI Consensus Algorithm under the Restricted Secant Inequality
di: Chakrabarti, Kushal, et al.
Pubblicazione: (2023)

Nonuniqueness and Convergence to Equivalent Solutions in Observer-based Inverse Reinforcement Learning
di: Town, Jared, et al.
Pubblicazione: (2022)

On the Global Convergence of Policy Gradient in Average Reward Markov Decision Processes
di: Kumar, Navdeep, et al.
Pubblicazione: (2024)

Safe Multi-Agent Reinforcement Learning with Convergence to Generalized Nash Equilibrium
di: Li, Zeyang, et al.
Pubblicazione: (2024)

Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs
di: Ding, Dongsheng, et al.
Pubblicazione: (2023)

Control in Stochastic Environment with Delays: A Model-based Reinforcement Learning Approach
di: Yao, Zhiyuan, et al.
Pubblicazione: (2024)

Dynamic Controlled Variables Based Dynamic Self-Optimizing Control
di: Zhou, Chenchen, et al.
Pubblicazione: (2026)

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

Reinforcement Learning Based Traffic Signal Design to Minimize Queue Lengths
di: Nandakumar, Anirud, et al.
Pubblicazione: (2025)

Non-Parametric Learning of Stochastic Differential Equations with Non-asymptotic Fast Rates of Convergence
di: Bonalli, Riccardo, et al.
Pubblicazione: (2023)

Convergence of Byzantine-Resilient Gradient Tracking via Probabilistic Edge Dropout
di: Dezhboro, Amirhossein, et al.
Pubblicazione: (2026)

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

ReACT: Reinforcement Learning for Controller Parametrization using B-Spline Geometries
di: Rudolf, Thomas, et al.
Pubblicazione: (2024)

Data-Driven Predictive Control of Nonholonomic Robots Based on a Bilinear Koopman Realization: Data Does Not Replace Geometry
di: Rosenfelder, Mario, et al.
Pubblicazione: (2024)

Active Learning-Based Optimization of Hydroelectric Turbine Startup to Minimize Fatigue Damage
di: Mai, Vincent, et al.
Pubblicazione: (2024)