Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Haolin, Wei, Chen-Yu, Zimmert, Julian
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback
par: Liu, Haolin, et autres
Publié: (2024)

Decision Making in Hybrid Environments: A Model Aggregation Approach
par: Liu, Haolin, et autres
Publié: (2025)

A Model Selection Approach for Corruption Robust Reinforcement Learning
par: Wei, Chen-Yu, et autres
Publié: (2021)

Optimal cross-learning for contextual bandits with unknown context distributions
par: Schneider, Jon, et autres
Publié: (2024)

A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive Delays
par: Masoudian, Saeed, et autres
Publié: (2023)

Incentive-compatible Bandits: Importance Weighting No More
par: Zimmert, Julian, et autres
Publié: (2024)

Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond
par: Chen, Fan, et autres
Publié: (2022)

Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition
par: Li, Long-Fei, et autres
Publié: (2024)

Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs
par: Kash, Ian A., et autres
Publié: (2022)

Non-stationary Bandit Convex Optimization: A Comprehensive Study
par: Liu, Xiaoqi, et autres
Publié: (2025)

Learning Adversarial MDPs with Stochastic Hard Constraints
par: Stradi, Francesco Emanuele, et autres
Publié: (2024)

NAN: A Training-Free Solution to Coefficient Estimation in Model Merging
par: Si, Chongjie, et autres
Publié: (2025)

Reinforcement Learning from Adversarial Preferences in Tabular MDPs
par: Tsuchiya, Taira, et autres
Publié: (2025)

Online Learning in MDPs with Partially Adversarial Transitions and Losses
par: Schlisselberg, Ofir, et autres
Publié: (2026)

Contextual Dynamic Pricing with Heterogeneous Buyers
par: Lykouris, Thodoris, et autres
Publié: (2025)

Efficient Model-Free Exploration in Low-Rank MDPs
par: Mhammedi, Zakaria, et autres
Publié: (2023)

Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs
par: Li, Long-Fei, et autres
Publié: (2024)

Breiman meets Bellman: Non-Greedy Decision Trees with MDPs
par: Kohler, Hector, et autres
Publié: (2023)

$κ$-Explorer: A Unified Framework for Active Model Estimation in MDPs
par: Gu, Xihe, et autres
Publié: (2026)

Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
par: Ito, Shinji, et autres
Publié: (2025)

Narrowing the Gap between Adversarial and Stochastic MDPs via Policy Optimization
par: Tiapkin, Daniil, et autres
Publié: (2024)

Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs
par: Zhang, Junkai, et autres
Publié: (2023)

TBDFiltering: Sample-Efficient Tree-Based Data Filtering
par: Busa-Fekete, Robert Istvan, et autres
Publié: (2026)

How Do Diffusion Models Improve Adversarial Robustness?
par: Yuezhang, Liu, et autres
Publié: (2025)

On the Complexity of Offline Reinforcement Learning with $Q^\star$-Approximation and Partial Coverage
par: Liu, Haolin, et autres
Publié: (2026)

An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction
par: van Erven, Tim, et autres
Publié: (2025)

Adaptive Estimation and Optimal Control in Offline Contextual MDPs without Stationarity
par: Bhattacharyya, Riddhiman, et autres
Publié: (2026)

Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification
par: Liu, Haolin, et autres
Publié: (2024)

Efficient Opportunistic Approachability
par: Marinov, Teodor Vanislavov, et autres
Publié: (2026)

Sample Complexity Bounds for Linear Constrained MDPs with a Generative Model
par: Liu, Xingtu, et autres
Publié: (2025)

Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPs
par: Tan, Kevin, et autres
Publié: (2024)

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

Modes of Sequence Models and Learning Coefficients
par: Chen, Zhongtian, et autres
Publié: (2025)

Interval Estimation of Coefficients in Penalized Regression Models of Insurance Data
par: Manna, Alokesh, et autres
Publié: (2024)

Time-Constrained Robust MDPs
par: Zouitine, Adil, et autres
Publié: (2024)

Estimation of the Learning Coefficient Using Empirical Loss
par: Takio, Tatsuyoshi, et autres
Publié: (2025)

Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs
par: Ding, Dongsheng, et autres
Publié: (2023)

Near-Optimal Sample Complexity for Online Constrained MDPs
par: Liu, Chang, et autres
Publié: (2026)

Reinforcement Learning for Infinite-Horizon Average-Reward Linear MDPs via Approximation by Discounted-Reward MDPs
par: Hong, Kihyuk, et autres
Publié: (2024)

Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel
par: Wang, Kaixin, et autres
Publié: (2023)