Imagen de Portada

Stationary Reweighting Yields Local Convergence of Soft Fitted Q-Iteration

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	van der Laan, Lars, Kallus, Nathan
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

Fitted $Q$ Evaluation Without Bellman Completeness via Stationary Weighting
por: van der Laan, Lars, et al.
Publicado: (2025)

Bellman Calibration for $V$-Learning in Offline Reinforcement Learning
por: van der Laan, Lars, et al.
Publicado: (2025)

Efficient Inference for Inverse Reinforcement Learning and Dynamic Discrete Choice Models
por: van der Laan, Lars, et al.
Publicado: (2025)

Nonparametric Instrumental Variable Inference with Many Weak Instruments
por: van der Laan, Lars, et al.
Publicado: (2025)

Inverse Reinforcement Learning with Just Classification and a Few Regressions
por: van der Laan, Lars, et al.
Publicado: (2025)

Reward Transfer from Inverse Reinforcement Learning: A Coupled Minimax Approach
por: Hao, Guang-Yuan, et al.
Publicado: (2026)

Automatic Debiased Machine Learning for Smooth Functionals of Nonparametric M-Estimands
por: van der Laan, Lars, et al.
Publicado: (2025)

Semiparametric Double Reinforcement Learning with Applications to Long-Term Causal Inference
por: van der Laan, Lars, et al.
Publicado: (2025)

A Researcher's Guide to Empirical Risk Minimization
por: van der Laan, Lars
Publicado: (2026)

Generalized Venn and Venn-Abers Calibration with Applications in Conformal Prediction
por: van der Laan, Lars, et al.
Publicado: (2025)

Smooth Non-Stationary Bandits
por: Jia, Su, et al.
Publicado: (2023)

Semiparametric Preference Optimization: Your Language Model is Secretly a Single-Index Model
por: Kallus, Nathan
Publicado: (2025)

Adaptive-TMLE for the Average Treatment Effect based on Randomized Controlled Trial Augmented with Real-World Data
por: van der Laan, Mark, et al.
Publicado: (2024)

Global Convergence of Iteratively Reweighted Least Squares for Robust Subspace Recovery
por: Lerman, Gilad, et al.
Publicado: (2025)

Generalisation in Multitask Fitted Q-Iteration and Offline Q-learning
por: Manda, Kausthubh, et al.
Publicado: (2025)

Generalized Fitted Q-Iteration with Clustered Data
por: Hu, Liyuan, et al.
Publicado: (2025)

Adaptive debiased machine learning using data-driven model selection techniques
por: van der Laan, Lars, et al.
Publicado: (2023)

Self-Calibrating Conformal Prediction
por: van der Laan, Lars, et al.
Publicado: (2024)

Exponential Convergence Guarantees for Iterative Markovian Fitting
por: Silveri, Marta Gentiloni, et al.
Publicado: (2025)

Calibeating Prediction-Powered Inference
por: van der Laan, Lars, et al.
Publicado: (2026)

Hybrid Meta-learners for Estimating Heterogeneous Treatment Effects
por: Liang, Zhongyuan, et al.
Publicado: (2025)

Combining T-learning and DR-learning: a framework for oracle-efficient estimation of causal contrasts
por: van der Laan, Lars, et al.
Publicado: (2024)

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

Estimating Heterogeneous Treatment Effects by Combining Weak Instruments and Observational Data
por: Oprescu, Miruna, et al.
Publicado: (2024)

On the role of surrogates in the efficient estimation of treatment effects with limited outcome data
por: Kallus, Nathan, et al.
Publicado: (2020)

Robust and Agnostic Learning of Conditional Distributional Treatment Effects
por: Kallus, Nathan, et al.
Publicado: (2022)

Variation Due to Regularization Tractably Recovers Bayesian Deep Learning
por: McInerney, James, et al.
Publicado: (2024)

Doubly robust inference via calibration
por: van der Laan, Lars, et al.
Publicado: (2024)

Demistifying Inference after Adaptive Experiments
por: Bibaut, Aurélien, et al.
Publicado: (2024)

Stabilized Inverse Probability Weighting via Isotonic Calibration
por: van der Laan, Lars, et al.
Publicado: (2024)

Multi-Armed Bandits with Interference
por: Jia, Su, et al.
Publicado: (2024)

LocalKMeans: Convergence of Lloyd's Algorithm with Distributed Local Iterations
por: Vardhan, Harsh, et al.
Publicado: (2025)

A Measure-Theoretic Finite-Sample Theory for Adaptive-Data Fitted Q-Iteration
por: Haussmann, Manuel, et al.
Publicado: (2026)

Exploration in the Limit
por: Cho, Brian M., et al.
Publicado: (2025)

Peeking with PEAK: Sequential, Nonparametric Composite Hypothesis Tests for Means of Multiple Data Streams
por: Cho, Brian, et al.
Publicado: (2024)

Robust Fitted-Q-Evaluation and Iteration under Sequentially Exogenous Unobserved Confounders
por: Bruns-Smith, David, et al.
Publicado: (2023)

The Context Gathering Decision Process: A POMDP Framework for Agentic Search
por: Kausik, Chinmaya, et al.
Publicado: (2026)

Low-Rank MDPs with Continuous Action Spaces
por: Bennett, Andrew, et al.
Publicado: (2023)

The Central Role of the Loss Function in Reinforcement Learning
por: Wang, Kaiwen, et al.
Publicado: (2024)

Is Cosine-Similarity of Embeddings Really About Similarity?
por: Steck, Harald, et al.
Publicado: (2024)