• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

Robust Offline Policy Evaluation and Optimization with Heavy-Tailed Rewards.

Jin ZhuRunzhe WanZhengling QiShikai LuoChengchun Shi
Published in: CoRR (2023)
Keyphrases
  • heavy tailed
  • policy evaluation
  • reinforcement learning
  • markov decision processes
  • least squares
  • model free