Image de couverture de livre

Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Zhiyong, Zhou, Dongruo, Lui, John C. S., Sun, Wen
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

Variance-Dependent Regret Bounds for Non-stationary Linear Bandits
par: Wang, Zhiyong, et autres
Publié: (2024)

Provable Zero-Shot Generalization in Offline Reinforcement Learning
par: Wang, Zhiyong, et autres
Publié: (2025)

Near-Optimal Second-Order Guarantees for Model-Based Adversarial Imitation Learning
par: Li, Shangzhe, et autres
Publié: (2025)

Federated In-Context Learning: Iterative Refinement for Improved Answer Quality
par: Wang, Ruhan, et autres
Publié: (2025)

More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning
par: Wang, Kaiwen, et autres
Publié: (2024)

Uncertainty-Aware Reward-Free Exploration with General Function Approximation
par: Zhang, Junkai, et autres
Publié: (2024)

Provably Efficient Representation Selection in Low-rank Markov Decision Processes: From Online to Offline RL
par: Zhang, Weitong, et autres
Publié: (2021)

Breaking the $\log(1/Δ_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids
par: Jin, Tianyuan, et autres
Publié: (2025)

Large Language Model-Enhanced Multi-Armed Bandits
par: Sun, Jiahang, et autres
Publié: (2025)

Quantum Algorithms for Projection-Free Sparse Convex Optimization
par: He, Jianhao, et autres
Publié: (2025)

Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding
par: Ma, Jiangyan, et autres
Publié: (2023)

Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path
par: Di, Qiwei, et autres
Publié: (2024)

On the Limits of Test-Time Compute: Sequential Reward Filtering for Better Inference
par: Yu, Yue, et autres
Publié: (2025)

FERA: Uncertainty-Aware Federated Reasoning for Large Language Models
par: Wang, Ruhan, et autres
Publié: (2026)

Second Order Bounds for Contextual Bandits with Function Approximation
par: Pacchiano, Aldo
Publié: (2024)

Instance-Dependent Continuous-Time Reinforcement Learning via Maximum Likelihood Estimation
par: Zhao, Runze, et autres
Publié: (2025)

ZEUS: Accelerating Diffusion Models with Only Second-Order Predictor
par: Wang, Yixiao, et autres
Publié: (2026)

Bridging RL Theory and Practice with the Effective Horizon
par: Laidlaw, Cassidy, et autres
Publié: (2023)

Second-Order Bounds for [0,1]-Valued Regression via Betting Loss
par: Li, Yinan, et autres
Publié: (2025)

CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing
par: Yang, Chen, et autres
Publié: (2024)

Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL
par: Wu, Ian, et autres
Publié: (2026)

Horizon Reduction Makes RL Scalable
par: Park, Seohong, et autres
Publié: (2025)

Improved Offline Contextual Bandits with Second-Order Bounds: Betting and Freezing
par: Ryu, J. Jon, et autres
Publié: (2025)

Online Clustering of Dueling Bandits
par: Wang, Zhiyong, et autres
Publié: (2025)

FM-EAC: Feature Model-based Enhanced Actor-Critic for Multi-Task Control in Dynamic Environments
par: Zhou, Quanxi, et autres
Publié: (2025)

Prior-Aligned Meta-RL: Thompson Sampling with Learned Priors and Guarantees in Finite-Horizon MDPs
par: Zhou, Runlin, et autres
Publié: (2025)

Second Order Methods for Bandit Optimization and Control
par: Suggala, Arun, et autres
Publié: (2024)

MINTS: Minimalist Thompson Sampling
par: Wang, Kaizheng
Publié: (2026)

A Split-Client Approach to Second-Order Optimization
par: Chayti, El Mahdi, et autres
Publié: (2025)

Policy Gradient with Second Order Momentum
par: Sun, Tianyu
Publié: (2025)

B3C: A Minimalist Approach to Offline Multi-Agent Reinforcement Learning
par: Kim, Woojun, et autres
Publié: (2025)

Return Augmented Decision Transformer for Off-Dynamics Reinforcement Learning
par: Wang, Ruhan, et autres
Publié: (2024)

How to Provably Improve Return Conditioned Supervised Learning?
par: Liu, Zhishuai, et autres
Publié: (2025)

A Minimalist Prompt for Zero-Shot Policy Learning
par: Song, Meng, et autres
Publié: (2024)

SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters
par: Xiao, Teng, et autres
Publié: (2025)

Minimalist Concept Erasure in Generative Models
par: Zhang, Yang, et autres
Publié: (2025)

Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward
par: Wen, Xuexiang, et autres
Publié: (2026)

Making RL with Preference-based Feedback Efficient via Randomization
par: Wu, Runzhe, et autres
Publié: (2023)

A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce
par: Xiong, Wei, et autres
Publié: (2025)

Order-Optimal Regret with Novel Policy Gradient Approaches in Infinite-Horizon Average Reward MDPs
par: Ganesh, Swetha, et autres
Publié: (2024)