R2PS: Worst-Case Robust Real-Time Pursuit Strategies under Partial Observability

Documenti analoghi

• ARAC: Adaptive Regularized Multi-Agent Soft Actor-Critic in Graph-Structured Adversarial Games
  di: Shi, Ruochuan, et al.
  Pubblicazione: (2025)
• Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games
  di: Lu, Runyu, et al.
  Pubblicazione: (2025)
• Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning
  di: Zhu, Yuanyang, et al.
  Pubblicazione: (2024)
• Streaming Reinforcement Learning under Partial Observability with Real-Time Recurrent Learning
  di: Farr, Noah, et al.
  Pubblicazione: (2026)
• Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement
  di: Wang, Zhi, et al.
  Pubblicazione: (2024)