Beyond Linear Attention: Softmax Transformers Implement In-Context Reinforcement Learning

Documenti analoghi

• Convergence and Emergence of In-Context Reinforcement Learning with Chain of Thought
  di: Xie, Zixuan, et al.
  Pubblicazione: (2026)
• Finite Sample Analysis of Linear Temporal Difference Learning with Arbitrary Features
  di: Xie, Zixuan, et al.
  Pubblicazione: (2025)
• Doubly Optimal Policy Evaluation for Reinforcement Learning
  di: Liu, Shuze Daniel, et al.
  Pubblicazione: (2024)
• Efficient Multi-Policy Evaluation for Reinforcement Learning
  di: Liu, Shuze Daniel, et al.
  Pubblicazione: (2024)
• Efficient Policy Evaluation with Safety Constraint for Reinforcement Learning
  di: Chen, Claire, et al.
  Pubblicazione: (2024)