One-Step Bellman Alignment Enables Provably Efficient Transfer in Online RL

Documenti analoghi

• Low-Rank Plus Sparse Matrix Transfer Learning under Growing Representations and Ambient Dimensions
  di: Chai, Jinhang, et al.
  Pubblicazione: (2026)
• Transition Transfer $Q$-Learning for Composite Markov Decision Processes
  di: Chai, Jinhang, et al.
  Pubblicazione: (2025)
• Deep Transfer $Q$-Learning for Offline Non-Stationary Reinforcement Learning
  di: Chai, Jinhang, et al.
  Pubblicazione: (2025)
• Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shift
  di: Zhang, Yi, et al.
  Pubblicazione: (2025)
• Learning to Hand Off: Provably Convergent Workflow Learning under Interface Constraints
  di: Li, Jiayu, et al.
  Pubblicazione: (2026)