RAT reformulates regularized natural policy gradients as vanilla gradients with a transformed advantage, computed efficiently via randomized block Kaczmarz iterations on on-policy data.
arXiv preprint arXiv:2104.06159 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Gato is a multi-modal, multi-task, multi-embodiment generalist policy using one transformer network to handle text, vision, games, and robotics tasks.