Order-Optimal Regret with Novel Policy Gradient Approaches in Infinite-Horizon Average Reward MDPs

Documenti analoghi

• Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes
  di: Bai, Qinbo, et al.
  Pubblicazione: (2023)
• Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm
  di: Bai, Qinbo, et al.
  Pubblicazione: (2024)
• A Sharper Global Convergence Analysis for Average Reward Reinforcement Learning via an Actor-Critic Approach
  di: Ganesh, Swetha, et al.
  Pubblicazione: (2024)
• Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach
  di: Ganesh, Swetha, et al.
  Pubblicazione: (2025)
• Improved Sample Complexity Analysis of Natural Policy Gradient Algorithm with General Parameterization for Infinite Horizon Discounted Reward Markov Decision Processes
  di: Mondal, Washim Uddin, et al.
  Pubblicazione: (2023)