FM3Q: Factorized Multi-Agent MiniMax Q-Learning for Two-Team Zero-Sum Markov Game

Documenti analoghi

• The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
  di: MiniMax, et al.
  Pubblicazione: (2026)
• Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning
  di: Zhu, Yuanyang, et al.
  Pubblicazione: (2024)
• A Hierarchical Deep Reinforcement Learning Framework for 6-DOF UCAV Air-to-Air Combat
  di: Chai, Jiajun, et al.
  Pubblicazione: (2022)
• Computing Ex Ante Equilibrium in Heterogeneous Zero-Sum Team Games
  di: Liu, Naming, et al.
  Pubblicazione: (2024)
• Bilevel Optimization over Saddle Points of Zero-Sum Markov Games
  di: Zheng, Zihao, et al.
  Pubblicazione: (2026)