Achieving the Asymptotically Optimal Sample Complexity of Offline Reinforcement Learning: A DRO-Based Approach

Documenti analoghi

• Model-Free Robust Reinforcement Learning with Sample Complexity Analysis
  di: Wang, Yudan, et al.
  Pubblicazione: (2024)
• Near-Optimal Sample Complexity for Iterated CVaR Reinforcement Learning with a Generative Model
  di: Deng, Zilong, et al.
  Pubblicazione: (2025)
• Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity
  di: Shi, Laixi, et al.
  Pubblicazione: (2022)
• Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation
  di: Wang, Yudan, et al.
  Pubblicazione: (2024)
• Sample Complexity Characterization for Linear Contextual MDPs
  di: Deng, Junze, et al.
  Pubblicazione: (2024)