Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes

Documenti analoghi

• Policy learning "without" overlap: Pessimism and generalized empirical Bernstein's inequality
  di: Jin, Ying, et al.
  Pubblicazione: (2022)
• Demystifying Spatial Confounding
  di: Dupont, Emiko, et al.
  Pubblicazione: (2023)
• Radial Neighbors for Provably Accurate Scalable Approximations of Gaussian Processes
  di: Zhu, Yichen, et al.
  Pubblicazione: (2022)
• Provably Efficient Posterior Sampling for Sparse Linear Regression via Measure Decomposition
  di: Montanari, Andrea, et al.
  Pubblicazione: (2024)
• Optimal Decision Rules Under Partial Identification
  di: Yata, Kohei
  Pubblicazione: (2021)