Imagen de Portada

An Improved Model-Free Decision-Estimation Coefficient with Applications in Adversarial MDPs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Haolin, Wei, Chen-Yu, Zimmert, Julian
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback
por: Liu, Haolin, et al.
Publicado: (2024)

Decision Making in Hybrid Environments: A Model Aggregation Approach
por: Liu, Haolin, et al.
Publicado: (2025)

A Model Selection Approach for Corruption Robust Reinforcement Learning
por: Wei, Chen-Yu, et al.
Publicado: (2021)

Optimal cross-learning for contextual bandits with unknown context distributions
por: Schneider, Jon, et al.
Publicado: (2024)

A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive Delays
por: Masoudian, Saeed, et al.
Publicado: (2023)

Incentive-compatible Bandits: Importance Weighting No More
por: Zimmert, Julian, et al.
Publicado: (2024)

Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond
por: Chen, Fan, et al.
Publicado: (2022)

Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition
por: Li, Long-Fei, et al.
Publicado: (2024)

Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs
por: Kash, Ian A., et al.
Publicado: (2022)

Non-stationary Bandit Convex Optimization: A Comprehensive Study
por: Liu, Xiaoqi, et al.
Publicado: (2025)

Learning Adversarial MDPs with Stochastic Hard Constraints
por: Stradi, Francesco Emanuele, et al.
Publicado: (2024)

NAN: A Training-Free Solution to Coefficient Estimation in Model Merging
por: Si, Chongjie, et al.
Publicado: (2025)

Reinforcement Learning from Adversarial Preferences in Tabular MDPs
por: Tsuchiya, Taira, et al.
Publicado: (2025)

Online Learning in MDPs with Partially Adversarial Transitions and Losses
por: Schlisselberg, Ofir, et al.
Publicado: (2026)

Contextual Dynamic Pricing with Heterogeneous Buyers
por: Lykouris, Thodoris, et al.
Publicado: (2025)

Efficient Model-Free Exploration in Low-Rank MDPs
por: Mhammedi, Zakaria, et al.
Publicado: (2023)

Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs
por: Li, Long-Fei, et al.
Publicado: (2024)

Breiman meets Bellman: Non-Greedy Decision Trees with MDPs
por: Kohler, Hector, et al.
Publicado: (2023)

$κ$-Explorer: A Unified Framework for Active Model Estimation in MDPs
por: Gu, Xihe, et al.
Publicado: (2026)

Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
por: Ito, Shinji, et al.
Publicado: (2025)

Narrowing the Gap between Adversarial and Stochastic MDPs via Policy Optimization
por: Tiapkin, Daniil, et al.
Publicado: (2024)

Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs
por: Zhang, Junkai, et al.
Publicado: (2023)

TBDFiltering: Sample-Efficient Tree-Based Data Filtering
por: Busa-Fekete, Robert Istvan, et al.
Publicado: (2026)

How Do Diffusion Models Improve Adversarial Robustness?
por: Yuezhang, Liu, et al.
Publicado: (2025)

On the Complexity of Offline Reinforcement Learning with $Q^\star$-Approximation and Partial Coverage
por: Liu, Haolin, et al.
Publicado: (2026)

An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction
por: van Erven, Tim, et al.
Publicado: (2025)

Adaptive Estimation and Optimal Control in Offline Contextual MDPs without Stationarity
por: Bhattacharyya, Riddhiman, et al.
Publicado: (2026)

Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification
por: Liu, Haolin, et al.
Publicado: (2024)

Efficient Opportunistic Approachability
por: Marinov, Teodor Vanislavov, et al.
Publicado: (2026)

Sample Complexity Bounds for Linear Constrained MDPs with a Generative Model
por: Liu, Xingtu, et al.
Publicado: (2025)

Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPs
por: Tan, Kevin, et al.
Publicado: (2024)

Teaching Precommitted Agents: Model-Free Policy Evaluation and Control in Quasi-Hyperbolic Discounted MDPs
por: Eshwar, S. R.
Publicado: (2025)

Modes of Sequence Models and Learning Coefficients
por: Chen, Zhongtian, et al.
Publicado: (2025)

Interval Estimation of Coefficients in Penalized Regression Models of Insurance Data
por: Manna, Alokesh, et al.
Publicado: (2024)

Time-Constrained Robust MDPs
por: Zouitine, Adil, et al.
Publicado: (2024)

Estimation of the Learning Coefficient Using Empirical Loss
por: Takio, Tatsuyoshi, et al.
Publicado: (2025)

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

Near-Optimal Sample Complexity for Online Constrained MDPs
por: Liu, Chang, et al.
Publicado: (2026)

Reinforcement Learning for Infinite-Horizon Average-Reward Linear MDPs via Approximation by Discounted-Reward MDPs
por: Hong, Kihyuk, et al.
Publicado: (2024)

Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel
por: Wang, Kaixin, et al.
Publicado: (2023)