Imagen de Portada

SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Mukherjee, Subhojyoti, Xie, Qiaomin, Hanna, Josiah, Nowak, Robert
Formato:	Preprint
Publicado:	2023
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning
por: Mukherjee, Subhojyoti, et al.
Publicado: (2024)

SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP
por: Mukherjee, Subhojyoti, et al.
Publicado: (2024)

Efficient and Interpretable Bandit Algorithms
por: Mukherjee, Subhojyoti, et al.
Publicado: (2023)

Stable Offline Value Function Learning with Bisimulation-based Representations
por: Pavse, Brahma S., et al.
Publicado: (2024)

Learning to Stabilize Online Reinforcement Learning in Unbounded State Spaces
por: Pavse, Brahma S., et al.
Publicado: (2023)

Off-Policy Evaluation from Logged Human Feedback
por: Bhargava, Aniruddha, et al.
Publicado: (2024)

On-Policy Policy Gradient Reinforcement Learning Without On-Policy Sampling
por: Corrado, Nicholas E., et al.
Publicado: (2023)

An Empirical Study on the Power of Future Prediction in Partially Observable Environments
por: Kwon, Jeongyeol, et al.
Publicado: (2024)

Experimental Design for Active Transductive Inference in Large Language Models
por: Mukherjee, Subhojyoti, et al.
Publicado: (2024)

Bias and Extrapolation in Markovian Linear Stochastic Approximation with Constant Stepsizes
por: Huo, Dongyan, et al.
Publicado: (2022)

Partial Policy Gradients for RL in LLMs
por: Mathur, Puneet, et al.
Publicado: (2026)

Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies
por: Corrado, Nicholas E., et al.
Publicado: (2025)

Wasserstein-p Central Limit Theorem Rates: From Local Dependence to Markov Chains
por: Zhang, Yixuan, et al.
Publicado: (2026)

Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation
por: Zhou, Hongyi, et al.
Publicado: (2025)

Robust Causal Bandits for Linear Models
por: Yan, Zirui, et al.
Publicado: (2023)

A Reduction Algorithm for Markovian Contextual Linear Bandits
por: Buyukkalayci, Kaan, et al.
Publicado: (2026)

Constant Stepsize Q-learning: Distributional Convergence, Bias and Extrapolation
por: Zhang, Yixuan, et al.
Publicado: (2024)

Coupling-based Convergence Diagnostic and Stepsize Scheme for Stochastic Gradient Descent
por: Li, Xiang, et al.
Publicado: (2024)

Restless Bandits with Average Reward: Breaking the Uniform Global Attractor Assumption
por: Hong, Yige, et al.
Publicado: (2023)

Experimental Design for Semiparametric Bandits
por: Kim, Seok-Jin, et al.
Publicado: (2025)

Improved Bound for Robust Causal Bandits with Linear Models
por: Yan, Zirui, et al.
Publicado: (2024)

Achieving Exponential Asymptotic Optimality in Average-Reward Restless Bandits without Global Attractor Assumption
por: Hong, Yige, et al.
Publicado: (2024)

Two-Timescale Linear Stochastic Approximation: Constant Stepsizes Go a Long Way
por: Kwon, Jeongyeol, et al.
Publicado: (2024)

Contextual Online Pricing with (Biased) Offline Data
por: Zhang, Yixuan, et al.
Publicado: (2025)

On the Peril of (Even a Little) Nonstationarity in Satisficing Regret Minimization
por: Zhang, Yixuan, et al.
Publicado: (2026)

Optimal Design for Human Preference Elicitation
por: Mukherjee, Subhojyoti, et al.
Publicado: (2024)

Adaptive Exploration for Data-Efficient General Value Function Evaluations
por: Jain, Arushi, et al.
Publicado: (2024)

Agentic Planning with Reasoning for Image Styling via Offline RL
por: Mukherjee, Subhojyoti, et al.
Publicado: (2026)

Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updates
por: Corrado, Nicholas E., et al.
Publicado: (2023)

Multi-Objective Alignment of Large Language Models Through Hypervolume Maximization
por: Mukherjee, Subhojyoti, et al.
Publicado: (2024)

Logits are All We Need to Adapt Closed Models
por: Hiranandani, Gaurush, et al.
Publicado: (2025)

Unichain and Aperiodicity are Sufficient for Asymptotic Optimality of Average-Reward Restless Bandits
por: Hong, Yige, et al.
Publicado: (2024)

Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction
por: Kiyohara, Haruka, et al.
Publicado: (2024)

Scaling Federated Linear Contextual Bandits via Sketching
por: Yang, Hantao, et al.
Publicado: (2026)

New Classes of the Greedy-Applicable Arm Feature Distributions in the Sparse Linear Bandit Problem
por: Ichikawa, Koji, et al.
Publicado: (2023)

Bandit Max-Min Fair Allocation
por: Harada, Tsubasa, et al.
Publicado: (2025)

C-kNN-LSH: A Nearest-Neighbor Algorithm for Sequential Counterfactual Inference
por: Wang, Jing, et al.
Publicado: (2026)

Wasserstein Distributionally Robust Policy Evaluation and Learning for Contextual Bandits
por: Shen, Yi, et al.
Publicado: (2023)

Design Experiments to Compare Multi-armed Bandit Algorithms
por: Meng, Huiling, et al.
Publicado: (2026)

Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling
por: Corrado, Nicholas E., et al.
Publicado: (2026)