Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity

Documenti analoghi

• Stochastic Shortest Path with Sparse Adversarial Costs
  di: Johnson, Emmeran, et al.
  Pubblicazione: (2025)
• On the necessity of adaptive regularisation:Optimal anytime online learning on $\boldsymbol{\ell_p}$-balls
  di: Johnson, Emmeran, et al.
  Pubblicazione: (2025)
• Scalable On-Policy Reinforcement Learning via Adaptive Batch Scaling
  di: Park, Jongchan
  Pubblicazione: (2026)
• Batch Bayesian Active Learning with Partial Batch Label Sampling
  di: Hu, Kangping, et al.
  Pubblicazione: (2025)
• Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariance
  di: McClellan, Joshua, et al.
  Pubblicazione: (2024)