Login / Signup

Unified PAC-Bayesian Study of Pessimism for Offline Policy Learning with Regularized Importance Sampling.

Imad AoualiVictor-Emmanuel BrunelDavid RohdeAnna Korba
Published in: CoRR (2024)
Keyphrases
  • importance sampling
  • learning problems
  • prior knowledge
  • learning algorithm
  • monte carlo
  • learning process
  • feature selection
  • least squares
  • markov chain
  • inductive inference