Cover Image

Parameter-free Optimal Rates for Nonlinear Semi-Norm Contractions with Applications to $Q$-Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Naskar, Ankur, Thoppe, Gugan, Gupta, Vijay
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Parameter-Free Federated TD Learning with Markov Noise in Heterogeneous Environments
by: Naskar, Ankur, et al.
Published: (2025)

Reinforcement Learning for Exponential Utility: Algorithms and Convergence in Discounted MDPs
by: Thoppe, Gugan, et al.
Published: (2026)

Does DQN Learn?
by: Gopalan, Aditya, et al.
Published: (2022)

Risk Estimation in a Markov Cost Process: Lower and Upper Bounds
by: Thoppe, Gugan, et al.
Published: (2023)

Reinforcement Learning with Quasi-Hyperbolic Discounting
by: Eshwar, S. R., et al.
Published: (2024)

Tight Convergence Rates for Online Distributed Linear Estimation with Adversarial Measurements
by: Roy, Nibedita, et al.
Published: (2026)

Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries
by: Ganesh, Swetha, et al.
Published: (2024)

Policy Gradient with Tree Expansion
by: Dalal, Gal, et al.
Published: (2023)

Adversary-Robust Learning from Fully Asynchronous Directional Derivative Estimates
by: Paul, Anik Kumar, et al.
Published: (2026)

What Can Be Recovered Under Sparse Adversarial Corruption? Assumption-Free Theory for Linear Measurements
by: Halder, Vishal, et al.
Published: (2025)

Reliable Policy Iteration: Performance Robustness Across Architecture and Environment Perturbations
by: Eshwar, S. R., et al.
Published: (2025)

Monotone and Conservative Policy Iteration Beyond the Tabular Case
by: Eshwar, S. R., et al.
Published: (2025)

Tessera: Secure, Near-Line-Rate Weight Streaming for UMA Edge Accelerators
by: Naskar, Animan
Published: (2026)

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

Towards Optimal Sobolev Norm Rates for the Vector-Valued Regularized Least-Squares Algorithm
by: Li, Zhu, et al.
Published: (2023)

The Shadow knows: Empirical Distributions of Minimum Spanning Acycles and Persistence Diagrams of Random Complexes
by: Fraiman, Nicolas, et al.
Published: (2020)

Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates
by: Maity, Sreejeet, et al.
Published: (2025)

Learning to Admit Optimally in an $M/M/k/k+N$ Queueing System with Unknown Service Rate
by: Adler, Saghar, et al.
Published: (2022)

Causal Multi-Task Demand Learning
by: Gupta, Varun, et al.
Published: (2026)

Sobolev Norm Learning Rates for Conditional Mean Embeddings
by: Talwai, Prem, et al.
Published: (2021)

A Parameter-Free Two-Bit Covariance Estimator with Improved Operator Norm Error Rate
by: Chen, Junren, et al.
Published: (2023)

Optimal Scaling Needs Optimal Norm
by: Filatov, Oleg, et al.
Published: (2025)

Precise Error Rates for Computationally Efficient Testing
by: Moitra, Ankur, et al.
Published: (2023)

Norm-Q: Effective Compression Method for Hidden Markov Models in Neuro-Symbolic Applications
by: Gao, Hanyuan, et al.
Published: (2025)

Minimax Optimal Q Learning with Nearest Neighbors
by: Zhao, Puning, et al.
Published: (2023)

A Nonlinear Separation Principle via Contraction Theory: Applications to Neural Networks, Control, and Learning
by: Gokhale, Anand, et al.
Published: (2026)

Stochastic Optimization in Semi-Discrete Optimal Transport: Convergence Analysis and Minimax Rate
by: Genans, Ferdinand, et al.
Published: (2025)

Rate-Optimal Noise Annealing in Semi-Dual Neural Optimal Transport: Tangential Identifiability, Off-Manifold Ambiguity, and Guaranteed Recovery
by: Chu, Raymond, et al.
Published: (2026)

Achieving $\varepsilon^{-2}$ Dependence for Average-Reward Q-Learning with a New Contraction Principle
by: Chen, Zijun, et al.
Published: (2026)

Learning Hidden Physics and System Parameters with Deep Operator Networks
by: Sarkar, Dibakar Roy, et al.
Published: (2024)

Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems
by: Suttle, Wesley A., et al.
Published: (2024)

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

DecomposeRL: Learning to Ask Useful, Informative, and Diverse Questions for Semi-Supervised, Traceable Claim Verification
by: Dipta, Shubhashis Roy, et al.
Published: (2026)

Bayesian Learning of Optimal Policies in Markov Decision Processes with Countably Infinite State-Space
by: Adler, Saghar, et al.
Published: (2023)

Toward a Unified Lyapunov-Certified ODE Convergence Analysis of Smooth Q-Learning with p-Norms
by: Lee, Donghwan, et al.
Published: (2024)

Model-free Posterior Sampling via Learning Rate Randomization
by: Tiapkin, Daniil, et al.
Published: (2023)

Neuro-mimetic Task-free Unsupervised Online Learning with Continual Self-Organizing Maps
by: Vaidya, Hitesh, et al.
Published: (2024)

Sequential Attention-based Sampling for Histopathological Analysis
by: G, Tarun, et al.
Published: (2025)

CafeQ: Calibration-free Quantization via Learned Transformations and Adaptive Rounding
by: Sun, Ziteng, et al.
Published: (2025)

Robustly Invertible Nonlinear Dynamics and the BiLipREN: Contracting Neural Models with Contracting Inverses
by: Zhang, Yurui, et al.
Published: (2025)