Denoised MDPs: Learning World Models Better Than the World Itself.

Tongzhou Wang Simon S. Du Antonio Torralba Phillip Isola Amy Zhang Yuandong Tian

Published in: CoRR (2022)

Keyphrases

reinforcement learning
learning algorithm
prior knowledge
learned models
qualitative models
probabilistic model
supervised learning
online learning
hidden variables
structured prediction
multiscale
least squares
denoising
learning systems
markov decision processes
learning tasks