Imagen de Portada

Beyond the Independence Assumption: Finite-Sample Guarantees for Deep Q-Learning under $τ$-Mixing

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Halgryn, Leon, Langer, Sophie, Meylahn, Janusz M., Hahn, E. Moritz
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

How social reinforcement learning can lead to metastable polarisation and the voter model
por: Meylahn, Benedikt V., et al.
Publicado: (2024)

On the Independence Assumption in Neurosymbolic Learning
por: van Krieken, Emile, et al.
Publicado: (2024)

Neurosymbolic Reasoning Shortcuts under the Independence Assumption
por: van Krieken, Emile, et al.
Publicado: (2025)

First Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptions
por: Shulgin, Egor, et al.
Publicado: (2025)

Conformal Risk Control under Non-Monotone Losses: Theory and Finite-Sample Guarantees
por: Aldirawi, Tareq, et al.
Publicado: (2026)

Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions
por: Pham, Le-Tuyet-Nhi, et al.
Publicado: (2026)

Reinforcement Learning for Control with Probabilistic Stability Guarantee: A Finite-Sample Approach
por: Han, Minghao, et al.
Publicado: (2026)

Prior-Aligned Meta-RL: Thompson Sampling with Learned Priors and Guarantees in Finite-Horizon MDPs
por: Zhou, Runlin, et al.
Publicado: (2025)

FaiREE: Fair Classification with Finite-Sample and Distribution-Free Guarantee
por: Li, Puheng, et al.
Publicado: (2022)

Challenging Assumptions in Learning Generic Text Style Embeddings
por: Ostheimer, Phil, et al.
Publicado: (2025)

Extrapolation Guarantees for Perturbation Modeling Under the Additive Latent Shift Assumption
por: von Kügelgen, Julius, et al.
Publicado: (2025)

Do Vendi Scores Converge with Finite Samples? Truncated Vendi Score for Finite-Sample Convergence Guarantees
por: Ospanov, Azim, et al.
Publicado: (2024)

Graphical Modelling without Independence Assumptions for Uncentered Data
por: Andrew, Bailey, et al.
Publicado: (2024)

From Set Convergence to Pointwise Convergence: Finite-Time Guarantees for Average-Reward Q-Learning with Adaptive Stepsizes
por: Chen, Zaiwei, et al.
Publicado: (2025)

Finite-Sample Analysis of Nonlinear Independent Component Analysis:Sample Complexity and Identifiability Bounds
por: Jiang, Yuwen
Publicado: (2026)

Q-Learning under Finite Model Uncertainty
por: Sester, Julian, et al.
Publicado: (2024)

A Minimal-Assumption Analysis of Q-Learning with Time-Varying Policies
por: Nanda, Phalguni, et al.
Publicado: (2025)

Finite-Sample Guarantees for Learning Dynamics in Zero-Sum Polymatrix Games
por: Faizal, Fathima Zarin, et al.
Publicado: (2024)

Conformal Mixed-Integer Constraint Learning with Feasibility Guarantees
por: Ovalle, Daniel, et al.
Publicado: (2025)

Sparse Representation Classification Beyond L1 Minimization and the Subspace Assumption
por: Shen, Cencheng, et al.
Publicado: (2015)

A Finite Sample Complexity Bound for Distributionally Robust Q-learning
por: Wang, Shengbo, et al.
Publicado: (2023)

Learning the Model While Learning Q: Finite-Time Sample Complexity of Online SyncMBQ
por: Lim, Han-Dong, et al.
Publicado: (2024)

Bivariate Matrix-valued Linear Regression (BMLR): Finite-sample performance under Identifiability and Sparsity Assumptions
por: Bettache, Nayel
Publicado: (2024)

Grables: Tabular Learning Beyond Independent Rows
por: Cucumides, Tamara, et al.
Publicado: (2026)

On the Sparsifiability of Correlation Clustering: Approximation Guarantees under Edge Sampling
por: Shihab, Ibne Farabi, et al.
Publicado: (2026)

CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity
por: Bhatt, Aditya, et al.
Publicado: (2019)

Achieving $ε^{-2}$ Sample Complexity for Single-Loop Actor-Critic under Minimal Assumptions
por: Hamza, Ishaq, et al.
Publicado: (2026)

A Measure-Theoretic Finite-Sample Theory for Adaptive-Data Fitted Q-Iteration
por: Haussmann, Manuel, et al.
Publicado: (2026)

PAC Guarantees for Reinforcement Learning: Sample Complexity, Coverage, and Structure
por: Steier, Joshua
Publicado: (2026)

On the Reduction of Variance and Overestimation of Deep Q-Learning
por: Sabry, Mohammed, et al.
Publicado: (2019)

BanditQ: Fair Bandits with Guaranteed Rewards
por: Sinha, Abhishek
Publicado: (2023)

An Exploratory Study on Automatic Identification of Assumptions in the Development of Deep Learning Frameworks
por: Yang, Chen, et al.
Publicado: (2024)

Convergence Of Consistency Model With Multistep Sampling Under General Data Assumptions
por: Chen, Yiding, et al.
Publicado: (2025)

Learning Optimal and Sample-Efficient Decision Policies with Guarantees
por: Shao, Daqian
Publicado: (2026)

Iterated $Q$-Network: Beyond One-Step Bellman Updates in Deep Reinforcement Learning
por: Vincent, Théo, et al.
Publicado: (2024)

Learning Guarantee of Reward Modeling Using Deep Neural Networks
por: Luo, Yuanhang, et al.
Publicado: (2025)

On Demographic Group Fairness Guarantees in Deep Learning
por: Luo, Yan, et al.
Publicado: (2024)

Explainable Clustering Beyond Worst-Case Guarantees
por: Fleissner, Maximilian, et al.
Publicado: (2024)

Efficient Techniques for Data Reconstruction, with Finite-Width Recovery Guarantees
por: Tansley, Edward, et al.
Publicado: (2026)

Uncovering Critical Sets of Deep Neural Networks via Sample-Independent Critical Lifting
por: Zhang, Leyang, et al.
Publicado: (2025)