Don't Forget the Critic: Value-Based Data Rehearsal for Multi-Cyclic Continual Reinforcement Learning

Documenti analoghi

• Towards Interactive Reinforcement Learning with Intrinsic Feedback
  di: Poole, Benjamin, et al.
  Pubblicazione: (2021)
• F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare
  di: Plyusov, Daniil, et al.
  Pubblicazione: (2026)
• Don't Forget It! Conditional Sparse Autoencoder Clamping Works for Unlearning
  di: Khoriaty, Matthew, et al.
  Pubblicazione: (2025)
• Don't Forget Imagination!
  di: Vityaev, Evgenii E., et al.
  Pubblicazione: (2025)
• Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsal
  di: Hu, Jifeng, et al.
  Pubblicazione: (2024)