Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients

Documenti analoghi

• Optimal Rates of Convergence for Entropy Regularization in Discounted Markov Decision Processes
  di: Müller, Johannes, et al.
  Pubblicazione: (2024)
• Accelerated Gradient Methods with Gradient Restart: Global Linear Convergence
  di: Bao, Chenglong, et al.
  Pubblicazione: (2024)
• Anderson Accelerated Primal-Dual Hybrid Gradient for solving LP
  di: Zhou, Yingxin, et al.
  Pubblicazione: (2025)
• Optimization in complex spaces with the Mixed Newton Method
  di: Bakhurin, Sergey, et al.
  Pubblicazione: (2022)
• A Massively Parallel Interior-Point Method for Arrowhead Linear Programs with Local Linking Structure
  di: Kempke, Nils-Christian, et al.
  Pubblicazione: (2024)