One-shot World Models Using a Transformer Trained on a Synthetic Prior

Documenti analoghi

• Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization
  di: Prasanna, Sai, et al.
  Pubblicazione: (2024)
• Hierarchical Transformers are Efficient Meta-Reinforcement Learners
  di: Shala, Gresa, et al.
  Pubblicazione: (2024)
• A Llama walks into the 'Bar': Efficient Supervised Fine-Tuning for Legal Reasoning in the Multi-state Bar Exam
  di: Fernandes, Rean, et al.
  Pubblicazione: (2025)
• TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting
  di: Moroshan, Vladyslav, et al.
  Pubblicazione: (2025)
• Inferring Behavior-Specific Context Improves Zero-Shot Generalization in Reinforcement Learning
  di: Ndir, Tidiane Camaret, et al.
  Pubblicazione: (2024)