Federated Q-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost

Documenti analoghi

• Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning
  di: Zhang, Haochen, et al.
  Pubblicazione: (2025)
• Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition
  di: Zheng, Zhong, et al.
  Pubblicazione: (2024)
• Q-Learning with Fine-Grained Gap-Dependent Regret
  di: Zhang, Haochen, et al.
  Pubblicazione: (2025)
• Federated Q-Learning: Linear Regret Speedup with Low Communication Cost
  di: Zheng, Zhong, et al.
  Pubblicazione: (2023)
• Gap-Dependent Bounds for Federated $Q$-learning
  di: Zhang, Haochen, et al.
  Pubblicazione: (2025)