Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning

Documenti analoghi

• Entropy Regularized Task Representation Learning for Offline Meta-Reinforcement Learning
  di: Nakhaei, Mohammadreza, et al.
  Pubblicazione: (2024)
• Contextual Latent World Models for Offline Meta Reinforcement Learning
  di: Nakheai, Mohammadreza, et al.
  Pubblicazione: (2026)
• iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning
  di: Scannell, Aidan, et al.
  Pubblicazione: (2024)
• Efficient Reinforcement Learning by Guiding Generalist World Models with Non-Curated Data
  di: Zhao, Yi, et al.
  Pubblicazione: (2025)
• Discrete Codebook World Models for Continuous Control
  di: Scannell, Aidan, et al.
  Pubblicazione: (2025)