Causal Learning for Decision Making (CLDM)

International Conference on Learning Representations (ICLR)

April 26, 2020

@CausalIclr ยท #CLDM2020


Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent Confounders

  • Andrew Bennett, Nathan Kallus, Lihong Li, Ali Mousavi
  • Research Track (Spotlight)
  • PDF