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

Documenti analoghi

• uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs
  di: Chen, Yu, et al.
  Pubblicazione: (2024)
• Finite-Time Convergence Analysis of ODE-based Generative Models for Stochastic Interpolants
  di: Liu, Yuhao, et al.
  Pubblicazione: (2025)
• Finite-Time Analysis of Discrete-Time Stochastic Interpolants
  di: Liu, Yuhao, et al.
  Pubblicazione: (2025)
• Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds
  di: Lee, Jongyeong, et al.
  Pubblicazione: (2024)
• Provably Efficient Partially Observable Risk-Sensitive Reinforcement Learning with Hindsight Observation
  di: Zhang, Tonghe, et al.
  Pubblicazione: (2024)