SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP

Documenti analoghi

• SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits
  di: Mukherjee, Subhojyoti, et al.
  Pubblicazione: (2023)
• Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning
  di: Mukherjee, Subhojyoti, et al.
  Pubblicazione: (2024)
• On-Policy Policy Gradient Reinforcement Learning Without On-Policy Sampling
  di: Corrado, Nicholas E., et al.
  Pubblicazione: (2023)
• Off-Policy Evaluation from Logged Human Feedback
  di: Bhargava, Aniruddha, et al.
  Pubblicazione: (2024)
• An Empirical Study on the Power of Future Prediction in Partially Observable Environments
  di: Kwon, Jeongyeol, et al.
  Pubblicazione: (2024)