Principled Fast and Meta Knowledge Learners for Continual Reinforcement Learning

Documenti analoghi

• Distributional Reinforcement Learning with Regularized Wasserstein Loss
  di: Sun, Ke, et al.
  Pubblicazione: (2022)
• A Distance-based Anomaly Detection Framework for Deep Reinforcement Learning
  di: Zhang, Hongming, et al.
  Pubblicazione: (2021)
• How Does Return Distribution in Distributional Reinforcement Learning Help Optimization?
  di: Sun, Ke, et al.
  Pubblicazione: (2022)
• Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Regularized Exploration in Reinforcement Learning
  di: Sun, Ke, et al.
  Pubblicazione: (2021)
• Trust Region Continual Learning as an Implicit Meta-Learner
  di: Wang, Zekun, et al.
  Pubblicazione: (2026)