Imagen de Portada

Provably Efficient UCB-type Algorithms For Learning Predictive State Representations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Ruiquan, Liang, Yingbin, Yang, Jing
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

Breaking the Computational Barrier: Provably Efficient Actor-Critic for Low-Rank MDPs
por: Huang, Ruiquan, et al.
Publicado: (2026)

Non-asymptotic Convergence of Training Transformers for Next-token Prediction
por: Huang, Ruiquan, et al.
Publicado: (2024)

Robust Offline Reinforcement Learning for Non-Markovian Decision Processes
por: Huang, Ruiquan, et al.
Publicado: (2024)

How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias
por: Huang, Ruiquan, et al.
Publicado: (2025)

Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning
por: Qiu, Shuang, et al.
Publicado: (2022)

Provable In-Context Learning of Nonlinear Regression with Transformers
por: Li, Hongbo, et al.
Publicado: (2025)

Agentic Transformers Provably Learn to Search via Reinforcement Learning
por: Yang, Tong, et al.
Publicado: (2026)

UCB-type Algorithm for Budget-Constrained Expert Learning
por: Latypov, Ilgam, et al.
Publicado: (2025)

Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups
por: Gao, Fengyu, et al.
Publicado: (2024)

Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent
por: Yang, Tong, et al.
Publicado: (2025)

Transformers Provably Learn Directed Acyclic Graphs via Kernel-Guided Mutual Information
por: Cheng, Yuan, et al.
Publicado: (2025)

Absorb and Converge: Provable Convergence Guarantee for Absorbing Discrete Diffusion Models
por: Liang, Yuchen, et al.
Publicado: (2025)

Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis
por: Huang, Ruiquan, et al.
Publicado: (2025)

In-Context Learning with Representations: Contextual Generalization of Trained Transformers
por: Yang, Tong, et al.
Publicado: (2024)

Algorithm Design for Online Meta-Learning with Task Boundary Detection
por: Sow, Daouda, et al.
Publicado: (2023)

Efficient Implementation of LinearUCB through Algorithmic Improvements and Vector Computing Acceleration for Embedded Learning Systems
por: Angioli, Marco, et al.
Publicado: (2025)

Clus-UCB: A Near-Optimal Algorithm for Clustered Bandits
por: Gore, Aakash, et al.
Publicado: (2025)

Provably Efficient Algorithms for S- and Non-Rectangular Robust MDPs with General Parameterization
por: Satheesh, Anirudh, et al.
Publicado: (2026)

Near-Optimal Partially Observable Reinforcement Learning with Partial Online State Information
por: Shi, Ming, et al.
Publicado: (2023)

Variance-Aware Linear UCB with Deep Representation for Neural Contextual Bandits
por: Bui, Ha Manh, et al.
Publicado: (2024)

Provable Low-Frequency Bias of In-Context Learning of Representations
por: Yang, Yongyi, et al.
Publicado: (2025)

Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning
por: Zhang, Hongming, et al.
Publicado: (2023)

Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret
por: Hu, Bingshan, et al.
Publicado: (2025)

Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning
por: Li, Na, et al.
Publicado: (2025)

Unlabeled Data Can Provably Enhance In-Context Learning of Transformers
por: Liu, Renpu, et al.
Publicado: (2026)

A Provably Convergent and Practical Algorithm for Gromov--Wasserstein Optimal Transport
por: Liang, Ling, et al.
Publicado: (2026)

Cooperative Multi-Agent Graph Bandits: UCB Algorithm and Regret Analysis
por: Paschalidis, Phevos, et al.
Publicado: (2024)

Efficient and Provable Algorithms for Covariate Shift
por: Adil, Deeksha, et al.
Publicado: (2025)

Polynomial Regret Concentration of UCB for Non-Deterministic State Transitions
por: Cömer, Can, et al.
Publicado: (2025)

Monitoring State Transitions in Markovian Systems with Sampling Cost
por: Saurav, Kumar, et al.
Publicado: (2025)

Replicable Bandits with UCB based Exploration
por: Deb, Rohan, et al.
Publicado: (2026)

Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games
por: Feng, Songtao, et al.
Publicado: (2023)

A Theoretical Analysis of Self-Supervised Learning for Vision Transformers
por: Huang, Yu, et al.
Publicado: (2024)

Learning with Shared Representations: Statistical Rates and Efficient Algorithms
por: Niu, Xiaochun, et al.
Publicado: (2024)

Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation
por: Pan, Pei-Chi, et al.
Publicado: (2026)

Empirical Comparison of Forgetting Mechanisms for UCB-based Algorithms on a Data-Driven Simulation Platform
por: Chen, Minxin
Publicado: (2025)

Greedy Sampling Is Provably Efficient for RLHF
por: Wu, Di, et al.
Publicado: (2025)

From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models
por: Liang, Yuchen, et al.
Publicado: (2026)

A UCB Bandit Algorithm for General ML-Based Estimators
por: Liu, Yajing, et al.
Publicado: (2026)

Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning
por: Cheng, Ziheng, et al.
Publicado: (2025)