Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It

Documenti analoghi

• Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction
  di: Kiyohara, Haruka, et al.
  Pubblicazione: (2024)
• Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits
  di: Shimizu, Tatsuhiro, et al.
  Pubblicazione: (2024)
• Off-Policy Evaluation and Learning for Matching Markets
  di: Hayashi, Yudai, et al.
  Pubblicazione: (2025)
• POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition
  di: Saito, Yuta, et al.
  Pubblicazione: (2024)
• A General Framework for Off-Policy Learning with Partially-Observed Reward
  di: Takehi, Rikiya, et al.
  Pubblicazione: (2025)