Imagen de Portada

Online Bandits with (Biased) Offline Data: Adaptive Learning under Distribution Mismatch

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cheung, Wang Chi, Lyu, Lixing
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Best Arm Identification with Possibly Biased Offline Data
por: Yang, Le, et al.
Publicado: (2025)

Efficiently Solving Discounted MDPs with Predictions on Transition Matrices
por: Lyu, Lixing, et al.
Publicado: (2025)

Episodic Contextual Bandits with Knapsacks under Conversion Models
por: Cheung, Wang Chi, et al.
Publicado: (2025)

Online Bandit Learning with Offline Preference Data for Improved RLHF
por: Agnihotri, Akhil, et al.
Publicado: (2024)

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

Pure Exploration for a Good Policy in Reinforcement Learning with Bandit Feedback
por: Li, Zitian, et al.
Publicado: (2026)

Direction-Aware Offline-to-Online Learning in Linear Contextual Bandits
por: Han, Zean, et al.
Publicado: (2026)

Offline Local Search for Online Stochastic Bandits
por: Benadè, Gerdus, et al.
Publicado: (2026)

Offline Clustering of Linear Bandits: The Power of Clusters under Limited Data
por: Liu, Jingyuan, et al.
Publicado: (2025)

Simulating Biases for Interpretable Fairness in Offline and Online Classifiers
por: Inácio, Ricardo, et al.
Publicado: (2025)

Benchmarks for Reinforcement Learning with Biased Offline Data and Imperfect Simulators
por: Linial, Ori, et al.
Publicado: (2024)

Adaptive Q-Chunking for Offline-to-Online Reinforcement Learning
por: Gireesh, Nandiraju, et al.
Publicado: (2026)

Offline Learning for Combinatorial Multi-armed Bandits
por: Liu, Xutong, et al.
Publicado: (2025)

Adaptive Client Sampling in Federated Learning via Online Learning with Bandit Feedback
por: Zhao, Boxin, et al.
Publicado: (2021)

Distributed quasi-Newton robust estimation under differential privacy
por: Wang, Chuhan, et al.
Publicado: (2024)

Planning to Go Out-of-Distribution in Offline-to-Online Reinforcement Learning
por: McInroe, Trevor, et al.
Publicado: (2023)

Adaptive Replay Buffer for Offline-to-Online Reinforcement Learning
por: Song, Chihyeon, et al.
Publicado: (2025)

ROAD: Adaptive Data Mixing for Offline-to-Online Reinforcement Learning via Bi-Level Optimization
por: Yang, Letian, et al.
Publicado: (2026)

Online Learning to Rank under Corruption: A Robust Cascading Bandits Approach
por: Ghaffari, Fatemeh, et al.
Publicado: (2025)

Adaptive Policy Selection and Fine-Tuning under Interaction Budgets for Offline-to-Online Reinforcement Learning
por: Bozkurt, Alper Kamil, et al.
Publicado: (2026)

Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning
por: Nakhaei, Mohammadreza, et al.
Publicado: (2024)

Leveraging Offline Data in Linear Latent Contextual Bandits
por: Kausik, Chinmaya, et al.
Publicado: (2024)

Multiclass Online Learnability under Bandit Feedback
por: Raman, Ananth, et al.
Publicado: (2023)

Bayesian Regret Minimization in Offline Bandits
por: Petrik, Marek, et al.
Publicado: (2023)

Group-Sensitive Offline Contextual Bandits
por: Guo, Yihong, et al.
Publicado: (2025)

Robust Policy Expansion for Offline-to-Online RL under Diverse Data Corruption
por: He, Longxiang, et al.
Publicado: (2025)

Active Advantage-Aligned Online Reinforcement Learning with Offline Data
por: Liu, Xuefeng, et al.
Publicado: (2025)

Analysis of On-policy Policy Gradient Methods under the Distribution Mismatch
por: Wang, Weizhen, et al.
Publicado: (2025)

Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity
por: Shi, Laixi, et al.
Publicado: (2022)

Behavior-Adaptive Q-Learning: A Unifying Framework for Offline-to-Online RL
por: Zu, Lipeng, et al.
Publicado: (2025)

Shift is Good: Mismatched Data Mixing Improves Test Performance
por: Medvedev, Marko, et al.
Publicado: (2025)

Sample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution Shift
por: Li, Bochao, et al.
Publicado: (2026)

Biased Dueling Bandits with Stochastic Delayed Feedback
por: Yi, Bongsoo, et al.
Publicado: (2024)

Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning
por: Wang, Qi, et al.
Publicado: (2023)

Offline Contextual Bandits in the Presence of New Actions
por: Kishimoto, Ren, et al.
Publicado: (2026)

Refined PAC-Bayes Bounds for Offline Bandits
por: Gouverneur, Amaury, et al.
Publicado: (2025)

Offline Contextual Bandit with Counterfactual Sample Identification
por: Gilotte, Alexandre, et al.
Publicado: (2025)

Model-based Offline RL via Robust Value-Aware Model Learning with Implicitly Differentiable Adaptive Weighting
por: Qiao, Zhongjian, et al.
Publicado: (2026)

Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline Data
por: Deng, Shilong, et al.
Publicado: (2025)

Bridging Online and Offline RL: Contextual Bandit Learning for Multi-Turn Code Generation
por: Chen, Ziru, et al.
Publicado: (2026)