Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games

Ähnliche Einträge

• R2PS: Worst-Case Robust Real-Time Pursuit Strategies under Partial Observability
  von: Lu, Runyu, et al.
  Veröffentlicht: (2025)
• ARAC: Adaptive Regularized Multi-Agent Soft Actor-Critic in Graph-Structured Adversarial Games
  von: Shi, Ruochuan, et al.
  Veröffentlicht: (2025)
• FM3Q: Factorized Multi-Agent MiniMax Q-Learning for Two-Team Zero-Sum Markov Game
  von: Hu, Guangzheng, et al.
  Veröffentlicht: (2024)
• Autonomous Decision Making for UAV Cooperative Pursuit-Evasion Game with Reinforcement Learning
  von: Zhao, Yang, et al.
  Veröffentlicht: (2024)
• Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning
  von: Zhu, Yuanyang, et al.
  Veröffentlicht: (2024)