Rohin Shah: Excited to share our work: collaboration requires understanding! In Overcooked, self-play doesn't gel with humans: it expects them to play like itself. (1/4)
Code: https://github.com/HumanCompatibleAI/overcooked_ai https://t.co/lqbzeTwoqr
4 replies, 376 likes
David Luan: Excited that Overcooked-like environments are being used to study cooperative multiagent RL!
I’m happy that the growth of indie gaming has led to new creative gameplay mechanics, which makes our jobs as researchers easier in that useful environments sometimes come to us :)
1 replies, 25 likes
Micah Carroll: Excited to finally release my first full-fledged research project, done under the amazing mentorship of @rohinmshah and @ancadianadragan!
1 replies, 20 likes
Ryan Lowe: This is cool! Really interesting work.
We've also found this in language learning: if you start with self-play, you often have to do some un-learning when fine tuning with humans (paper coming soon!)
0 replies, 10 likes
mat kelcey: "On the Utility of Learning about Humans for Human-AI Coordination" https://arxiv.org/abs/1910.05789 https://t.co/55OMLV2nH3
0 replies, 9 likes
Julian Togelius: Very cool!
0 replies, 2 likes
Found on Oct 21 2019 at https://arxiv.org/pdf/1910.05789.pdf