Copertina

Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Huang, Jiayi, Zhong, Han, Wang, Liwei, Yang, Lin F.
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm
di: Vakili, Sattar, et al.
Pubblicazione: (2024)

Minimax Optimal Variance-Aware Regret Bounds for Multinomial Logistic MDPs
di: Boudart, Pierre, et al.
Pubblicazione: (2026)

Kernelized Reinforcement Learning with Order Optimal Regret Bounds
di: Vakili, Sattar, et al.
Pubblicazione: (2023)

Robust Offline Reinforcement learning with Heavy-Tailed Rewards
di: Zhu, Jin, et al.
Pubblicazione: (2023)

Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret
di: Zhong, Han, et al.
Pubblicazione: (2023)

$(ε, u)$-Adaptive Regret Minimization in Heavy-Tailed Bandits
di: Genalti, Gianmarco, et al.
Pubblicazione: (2023)

Gap-Dependent Bounds for Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation
di: Zhang, Haochen, et al.
Pubblicazione: (2026)

Misspecified $Q$-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation Error
di: Du, Ally Yalei, et al.
Pubblicazione: (2024)

Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning
di: Moradipari, Ahmadreza, et al.
Pubblicazione: (2023)

Regret Bounds and Reinforcement Learning Exploration of EXP-based Algorithms
di: Xu, Mengfan, et al.
Pubblicazione: (2020)

Refining Minimax Regret for Unsupervised Environment Design
di: Beukman, Michael, et al.
Pubblicazione: (2024)

Variance-Dependent Regret Lower Bounds for Contextual Bandits
di: He, Jiafan, et al.
Pubblicazione: (2025)

On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality
di: Hu, Jerry Yao-Chieh, et al.
Pubblicazione: (2024)

Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds
di: Liang, Hao, et al.
Pubblicazione: (2022)

Variance-Dependent Regret Bounds for Non-stationary Linear Bandits
di: Wang, Zhiyong, et al.
Pubblicazione: (2024)

RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning
di: Feng, Sicheng, et al.
Pubblicazione: (2025)

Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning
di: Liu, Zhishuai, et al.
Pubblicazione: (2024)

Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling
di: Xu, Jiawei, et al.
Pubblicazione: (2024)

Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards
di: Tajdini, Artin, et al.
Pubblicazione: (2025)

The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
di: Fluri, Lukas, et al.
Pubblicazione: (2024)

Minimax Optimality and Spectral Routing for Majority-Vote Ensembles under Markov Dependence
di: Shihab, Ibne Farabi, et al.
Pubblicazione: (2026)

Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning
di: Shan, Zikang, et al.
Pubblicazione: (2026)

TailedTS: Benchmark Dataset for Heavy-Tailed Time Series Prediction and Periodicity Quantification
di: Chen, Xinyu, et al.
Pubblicazione: (2026)

Constraints as Rewards: Reinforcement Learning for Robots without Reward Functions
di: Ishihara, Yu, et al.
Pubblicazione: (2025)

On Tackling Complex Tasks with Reward Machines and Signal Temporal Logics
di: Ruiz, Ana María Gómez, et al.
Pubblicazione: (2026)

Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits
di: Hou, Yunlong, et al.
Pubblicazione: (2024)

No-Regret Reinforcement Learning in Smooth MDPs
di: Maran, Davide, et al.
Pubblicazione: (2024)

Concentration Tail-Bound Analysis of Coevolutionary and Bandit Learning Algorithms
di: Lehre, Per Kristian, et al.
Pubblicazione: (2024)

No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery
di: Rutherford, Alexander, et al.
Pubblicazione: (2024)

Transformable Gaussian Reward Function for Socially-Aware Navigation with Deep Reinforcement Learning
di: Kim, Jinyeob, et al.
Pubblicazione: (2024)

On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation
di: Huang, Jiawei, et al.
Pubblicazione: (2023)

The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models
di: Li, Zichao, et al.
Pubblicazione: (2025)

Efficient Reinforcement Learning in Probabilistic Reward Machines
di: Lin, Xiaofeng, et al.
Pubblicazione: (2024)

Regret-Based Defense in Adversarial Reinforcement Learning
di: Belaire, Roman, et al.
Pubblicazione: (2023)

Regret-Free Reinforcement Learning for LTL Specifications
di: Majumdar, Rupak, et al.
Pubblicazione: (2024)

Attention-Guided Reward for Reinforcement Learning-based Jailbreak against Large Reasoning Models
di: Lin, Zheng, et al.
Pubblicazione: (2026)

Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviors
di: Ke, Jingyang, et al.
Pubblicazione: (2025)

Integrating Reinforcement Learning, Action Model Learning, and Numeric Planning for Tackling Complex Tasks
di: Benyamin, Yarin, et al.
Pubblicazione: (2025)

Are Bounded Contracts Learnable and Approximately Optimal?
di: Chen, Yurong, et al.
Pubblicazione: (2024)

Text2Reward: Reward Shaping with Language Models for Reinforcement Learning
di: Xie, Tianbao, et al.
Pubblicazione: (2023)