Image de couverture de livre

Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Qian, Jian, Hu, Haichen, Simchi-Levi, David
Format:	Preprint
Publié:	2024
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

Model-Based Reinforcement Learning with Double Oracle Efficiency in Policy Optimization and Offline Estimation
par: Hu, Haichen, et autres
Publié: (2026)

Interleaved Resampling and Refitting: Data and Compute-Efficient Evaluation of Black-Box Predictors
par: Hu, Haichen, et autres
Publié: (2026)

Perturbing the Derivative: Doubly Wild Refitting for Model-Free Evaluation of Opaque Machine Learning Predictors
par: Hu, Haichen, et autres
Publié: (2025)

Perturbing the Derivative: Wild Refitting for Model-Free Evaluation of Machine Learning Models under Bregman Losses
par: Hu, Haichen, et autres
Publié: (2025)

Pre-Trained AI Model Assisted Online Decision-Making under Missing Covariates: A Theoretical Perspective
par: Hu, Haichen, et autres
Publié: (2025)

Contextual Online Decision Making with Infinite-Dimensional Functional Regression
par: Hu, Haichen, et autres
Publié: (2025)

Constrained Online Decision-Making: A Unified Framework
par: Hu, Haichen, et autres
Publié: (2025)

On the Optimal Regret of Locally Private Linear Contextual Bandit
par: Li, Jiachun, et autres
Publié: (2024)

Exploration-Exploitation Tradeoff in Universal Lossy Compression
par: Weinberger, Nir, et autres
Publié: (2025)

Neural Exploitation and Exploration of Contextual Bandits
par: Ban, Yikun, et autres
Publié: (2023)

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

From Confounding to Learning: Dynamic Service Fee Pricing on Third-Party Platforms
par: Ai, Rui, et autres
Publié: (2025)

Learning to Price with Resource Constraints: From Full Information to Machine-Learned Prices
par: Ao, Ruicheng, et autres
Publié: (2025)

Near-Optimal Regret for Policy Optimization in Contextual MDPs with General Offline Function Approximation
par: Levy, Orin, et autres
Publié: (2026)

Sample and Oracle Efficient Reinforcement Learning for MDPs with Linearly-Realizable Value Functions
par: Mhammedi, Zakaria
Publié: (2024)

Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits
par: Qin, Hao, et autres
Publié: (2026)

Sobolev Norm Learning Rates for Conditional Mean Embeddings
par: Talwai, Prem, et autres
Publié: (2021)

Exploration Implies Data Augmentation: Reachability and Generalisation in Contextual MDPs
par: Weltevrede, Max, et autres
Publié: (2024)

Regret-Oracle Complexity Tradeoffs in Agnostic Online Learning
par: Attias, Idan, et autres
Publié: (2026)

Navigating the Exploration-Exploitation Tradeoff in Inference-Time Scaling of Diffusion Models
par: Su, Xun, et autres
Publié: (2025)

Improving the Estimation of Lifetime Effects in A/B Testing via Treatment Locality
par: Chen, Shuze, et autres
Publié: (2024)

Optimal Adaptive Experimental Design for Estimating Treatment Effect
par: Li, Jiachun, et autres
Publié: (2024)

Prediction-Guided Active Experiments
par: Ao, Ruicheng, et autres
Publié: (2024)

Beyond ATE: Multi-Criteria Design for A/B Testing
par: Li, Jiachun, et autres
Publié: (2025)

Is Pure Exploitation Sufficient in Exogenous MDPs with Linear Function Approximation?
par: Liang, Hao, et autres
Publié: (2026)

Offline-Online Reinforcement Learning for Linear Mixture MDPs
par: Zhang, Zhongjun, et autres
Publié: (2026)

Exploitation Over Exploration: Unmasking the Bias in Linear Bandit Recommender Offline Evaluation
par: Pires, Pedro R., et autres
Publié: (2025)

A Simple and Optimal Policy Design with Safety against Heavy-Tailed Risk for Stochastic Bandits
par: Simchi-Levi, David, et autres
Publié: (2022)

Partial Identification under Missing Data Using Weak Shadow Variables from Pretrained Models
par: Chen, Hongyu, et autres
Publié: (2026)

The Value of Information in Resource-Constrained Pricing
par: Ao, Ruicheng, et autres
Publié: (2026)

Privacy Preserving Adaptive Experiment Design
par: Li, Jiachun, et autres
Publié: (2024)

Regret Distribution in Stochastic Bandits: Optimal Trade-off between Expectation and Tail Risk
par: Simchi-Levi, David, et autres
Publié: (2023)

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

Sample Complexity Characterization for Linear Contextual MDPs
par: Deng, Junze, et autres
Publié: (2024)

Eluder-based Regret for Stochastic Contextual MDPs
par: Levy, Orin, et autres
Publié: (2022)

On the Reliability Limits of LLM-Based Multi-Agent Planning
par: Ao, Ruicheng, et autres
Publié: (2026)

ORLoopBench: Solver-in-the-Loop Benchmarks for Self-Correction and Behavioral Rationality in Operations Research
par: Ao, Ruicheng, et autres
Publié: (2026)

OptiRepair: Closed-Loop Diagnosis and Repair of Supply Chain Optimization Models with LLM Agents
par: Ao, Ruicheng, et autres
Publié: (2026)

A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPs
par: Hong, Kihyuk, et autres
Publié: (2024)

In-context Exploration-Exploitation for Reinforcement Learning
par: Dai, Zhenwen, et autres
Publié: (2024)