Login / Signup

Distributional Offline Policy Evaluation with Predictive Error Guarantees.

Runzhe WuMasatoshi UeharaWen Sun
Published in: CoRR (2023)
Keyphrases
  • policy evaluation
  • variance reduction
  • least squares
  • temporal difference
  • reinforcement learning
  • monte carlo
  • function approximation
  • model free
  • policy iteration
  • markov decision processes
  • matrix inversion
  • sample size