Cover Image

Best-of-Both-Worlds for Heavy-Tailed Markov Decision Processes

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Yu, Liu, Yuhao, Huang, Jiatai, Du, Yihan, Huang, Longbo
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs
by: Chen, Yu, et al.
Published: (2024)

Finite-Time Convergence Analysis of ODE-based Generative Models for Stochastic Interpolants
by: Liu, Yuhao, et al.
Published: (2025)

Finite-Time Analysis of Discrete-Time Stochastic Interpolants
by: Liu, Yuhao, et al.
Published: (2025)

Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds
by: Lee, Jongyeong, et al.
Published: (2024)

Provably Efficient Partially Observable Risk-Sensitive Reinforcement Learning with Hindsight Observation
by: Zhang, Tonghe, et al.
Published: (2024)

Best-of-Both-Worlds Algorithms for Linear Contextual Bandits
by: Kuroki, Yuko, et al.
Published: (2023)

The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection
by: Zhang, Qingyang, et al.
Published: (2024)

Finite-time Convergence Analysis of Actor-Critic with Evolving Reward
by: Hu, Rui, et al.
Published: (2025)

Horizon-Free Regret for Linear Markov Decision Processes
by: Zhang, Zihan, et al.
Published: (2024)

Best-of-Both Worlds for linear contextual bandits with paid observations
by: Boyer, Nathan, et al.
Published: (2025)

Best-of-Both-Worlds Policy Optimization for CMDPs with Bandit Feedback
by: Stradi, Francesco Emanuele, et al.
Published: (2024)

Best of Both Worlds: Regret Minimization versus Minimax Play
by: Müller, Adrian, et al.
Published: (2025)

Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback
by: Schlisselberg, Ofir, et al.
Published: (2025)

Continuous K-Max Bandits
by: Chen, Yu, et al.
Published: (2025)

Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and Practicality
by: Kim, Chaiwon, et al.
Published: (2025)

Efficient Best-of-Both-Worlds Algorithms for Contextual Combinatorial Semi-Bandits
by: Li, Mengmeng, et al.
Published: (2025)

Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation
by: Chen, Yu, et al.
Published: (2024)

Best of Both Worlds: Practical and Theoretically Optimal Submodular Maximization in Parallel
by: Chen, Yixin, et al.
Published: (2021)

LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits
by: Kato, Masahiro, et al.
Published: (2024)

A Best-of-Both-Worlds Algorithm for Constrained MDPs with Long-Term Constraints
by: Germano, Jacopo, et al.
Published: (2023)

Layer-Aware Influence for Online Data Valuation Estimation
by: Yang, Ziao, et al.
Published: (2025)

Best of Both Worlds: Advantages of Hybrid Graph Sequence Models
by: Behrouz, Ali, et al.
Published: (2024)

Monitored Markov Decision Processes
by: Parisi, Simone, et al.
Published: (2024)

A Further Efficient Algorithm with Best-of-Both-Worlds Guarantees for $m$-Set Semi-Bandit Problem
by: Chen, Botao, et al.
Published: (2026)

Mixed Sparsity Training: Achieving 4$\times$ FLOP Reduction for Transformer Pretraining
by: Hu, Pihe, et al.
Published: (2024)

Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds
by: Ito, Shinji, et al.
Published: (2024)

Adversarial Network Optimization under Bandit Feedback: Maximizing Utility in Non-Stationary Multi-Hop Networks
by: Dai, Yan, et al.
Published: (2024)

PowerFlow: Unlocking the Dual Nature of LLMs via Principled Distribution Matching
by: Chen, Ruishuo, et al.
Published: (2026)

Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models
by: Ziani, Abdelhakim, et al.
Published: (2026)

Tail Annealing for Heavy-Tailed Flow Matching
by: Pachebat, Jean
Published: (2026)

Generalized Linear Markov Decision Process
by: Zhang, Sinian, et al.
Published: (2025)

Federated Control in Markov Decision Processes
by: Jin, Hao, et al.
Published: (2024)

Asymptotic Classification Error for Heavy-Tailed Renewal Processes
by: Rong, Xinhui, et al.
Published: (2024)

Real-Time Parallel Counterfactual Regret Minimization
by: Li, Boning, et al.
Published: (2026)

A Best-of-Both-Worlds Proof for Tsallis-INF without Fenchel Conjugates
by: Lee, Wei-Cheng, et al.
Published: (2025)

OCMDP: Observation-Constrained Markov Decision Process
by: Wang, Taiyi, et al.
Published: (2024)

Follow-the-Perturbed-Leader Approaches Best-of-Both-Worlds for the m-Set Semi-Bandit Problems
by: Zhan, Jingxin, et al.
Published: (2025)

Learning to Bid in FCR Markets: A Best-of-Both-Worlds Approach
by: Potfer, Marius, et al.
Published: (2026)

Clip Body and Tail Separately: High Probability Guarantees for DPSGD with Heavy Tails
by: Sha, Haichao, et al.
Published: (2024)

Stochastic Bilevel Optimization with Heavy-Tailed Noise
by: Liu, Zhuanghua, et al.
Published: (2025)