Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learning

Documenti analoghi

• Lifelong and Continual Learning Dialogue Systems
  di: Mazumder, Sahisnu, et al.
  Pubblicazione: (2022)
• Continual Learning Using a Kernel-Based Method Over Foundation Models
  di: Momeni, Saleh, et al.
  Pubblicazione: (2024)
• In-context Continual Learning Assisted by an External Continual Learner
  di: Momeni, Saleh, et al.
  Pubblicazione: (2024)
• Self-Initiated Open World Learning for Autonomous AI Agents
  di: Liu, Bing, et al.
  Pubblicazione: (2021)
• Probabilistic Shielding for Safe Reinforcement Learning
  di: Court, Edwin Hamel-De le, et al.
  Pubblicazione: (2025)