Distributed Zeroth-Order Policy Gradient for Networked Multi-agent Reinforcement Learning from Human Feedback

Documenti analoghi

• Distributed primal-dual algorithm for constrained multi-agent reinforcement learning under coupled policies
  di: Dai, Pengcheng, et al.
  Pubblicazione: (2025)
• Distributed Neural Policy Gradient Algorithm for Global Convergence of Networked Multi-Agent Reinforcement Learning
  di: Dai, Pengcheng, et al.
  Pubblicazione: (2025)
• Distributed scalable coupled policy algorithm for networked multi-agent reinforcement learning
  di: Dai, Pengcheng, et al.
  Pubblicazione: (2025)
• Variance-Reduced Gradient Estimator for Nonconvex Zeroth-Order Distributed Optimization
  di: Mu, Huaiyi, et al.
  Pubblicazione: (2024)
• M3HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality
  di: Wang, Ziyan, et al.
  Pubblicazione: (2025)