Imagen de Portada

Finite-Time Error Analysis of Soft Q-Learning: Switching System Approach

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jeong, Narim, Lee, Donghwan
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

Safe-Support Q-Learning: Learning without Unsafe Exploration
por: Lim, Yeeun, et al.
Publicado: (2026)

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

Stochastic Primal-Dual Q-Learning
por: Jeong, Narim, et al.
Publicado: (2018)

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

A Switching System Theory of Q-Learning with Linear Function Approximation
por: Lee, Donghwan, et al.
Publicado: (2026)

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

Sign-Separated Finite-Time Error Analysis of Q-Learning
por: Lee, Donghwan
Publicado: (2026)

Finite-Time Analysis of Temporal Difference Learning with Experience Replay
por: Lim, Han-Dong, et al.
Publicado: (2023)

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

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

Suppressing Overestimation in Q-Learning through Adversarial Behaviors
por: Lee, HyeAnn, et al.
Publicado: (2023)

Regularized Q-learning
por: Lim, Han-Dong, et al.
Publicado: (2022)

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

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

Periodic Regularized Q-Learning
por: Yang, Hyukjun, et al.
Publicado: (2026)

Soft Deterministic Policy Gradient with Gaussian Smoothing
por: Na, Hyunjun, et al.
Publicado: (2026)

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

Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning
por: Park, Jongchan, et al.
Publicado: (2025)

R-GTD: A Geometric Analysis of Gradient Temporal-Difference Learning in Singular Regimes
por: Na, Hyunjun, et al.
Publicado: (2026)

A finite time analysis of distributed Q-learning
por: Lim, Han-Dong, et al.
Publicado: (2024)

Understanding the theoretical properties of projected Bellman equation, linear Q-learning, and approximate value iteration
por: Lim, Han-Dong, et al.
Publicado: (2025)

A Discrete-Time Switching System Analysis of Q-learning
por: Lee, Donghwan, et al.
Publicado: (2021)

Analysis of Off-Policy $n$-Step TD-Learning with Linear Function Approximation
por: Lim, Han-Dong, et al.
Publicado: (2025)

Switching-Geometry Analysis of Deflated Q-Value Iteration
por: Lee, Donghwan
Publicado: (2026)

Finite-Time Bounds for Average-Reward Fitted Q-Iteration
por: Lee, Jongmin, et al.
Publicado: (2025)

Backstepping Temporal Difference Learning
por: Lim, Han-Dong, et al.
Publicado: (2023)

Taming the Adversary: Stable Minimax Deep Deterministic Policy Gradient via Fractional Objectives
por: Lee, Taeho, et al.
Publicado: (2026)

Studying the Korean Word-Chain Game with RLVR: Mitigating Reward Conflicts via Curriculum Learning
por: Rho, Donghwan
Publicado: (2025)

Finite-Time Error Bounds for Greedy-GQ
por: Wang, Yue, et al.
Publicado: (2022)

Soft Contrastive Learning for Time Series
por: Lee, Seunghan, et al.
Publicado: (2023)

Adaptive Policy Backbone via Shared Network
por: Park, Bumgeun, et al.
Publicado: (2025)

Bellman Residual Minimization for Control: Geometry, Stationarity, and Convergence
por: Lee, Donghwan, et al.
Publicado: (2026)

Boosting Soft Q-Learning by Bounding
por: Adamczyk, Jacob, et al.
Publicado: (2024)

A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks
por: Moniri, Behrad, et al.
Publicado: (2023)

New Versions of Gradient Temporal Difference Learning
por: Lee, Donghwan, et al.
Publicado: (2021)

A primal-dual perspective for distributed TD-learning
por: Lim, Han-Dong, et al.
Publicado: (2023)

A Finite-Time Analysis of TD Learning with Linear Function Approximation without Projections or Strong Convexity
por: Lee, Wei-Cheng, et al.
Publicado: (2025)

Finite-Time Analysis of Discrete-Time Stochastic Interpolants
por: Liu, Yuhao, et al.
Publicado: (2025)

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