Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Halgryn, Leon, Langer, Sophie, Meylahn, Janusz M., Hahn, E. Moritz
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

BanditQ: Fair Bandits with Guaranteed Rewards
di: Sinha, Abhishek
Pubblicazione: (2023)

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

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

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

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

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

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

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

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

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