LOLA-pytorch
LOLA-pytorch copied to clipboard
Published
20 hours ago •
agakshat
agakshat
Implementing the Learning with Opponent Learning Awareness paper (https://blog.openai.com/learning-to-model-other-minds/)
[Update July 2018] The authors have released their official implementation of LOLA here
This is an implementation of the Learning with Opponent Learning Awareness paper by Foerster et al.
It is a work in progress. Have only done the exact updates on Prisoners' Dilemma till now, to get the basics working.
agakshat