Model-Based Reinforcement Learning with Double Oracle Efficiency in Policy Optimization and Offline Estimation

Documenti analoghi

• Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff
  di: Qian, Jian, et al.
  Pubblicazione: (2024)
• Perturbing the Derivative: Wild Refitting for Model-Free Evaluation of Machine Learning Models under Bregman Losses
  di: Hu, Haichen, et al.
  Pubblicazione: (2025)
• Perturbing the Derivative: Doubly Wild Refitting for Model-Free Evaluation of Opaque Machine Learning Predictors
  di: Hu, Haichen, et al.
  Pubblicazione: (2025)
• Pre-Trained AI Model Assisted Online Decision-Making under Missing Covariates: A Theoretical Perspective
  di: Hu, Haichen, et al.
  Pubblicazione: (2025)
• Interleaved Resampling and Refitting: Data and Compute-Efficient Evaluation of Black-Box Predictors
  di: Hu, Haichen, et al.
  Pubblicazione: (2026)