Michael Dennis

Before joining CHAI, Michael worked in theoretical computer science. He is working to close the gap between game theoretic principles and current approaches to multi-agent learning in order to provide better assurances of both performance and stability in these systems. Currently, this takes the form of work on Unsupervised Environment Design (UED), which aims to build complex and challenging environments automatically to promote efficient learning and transfer. This framework has deep connections to decision theory, which allows us to make guarantees about how the resulting policies would perform in human-designed environments, without having ever trained on them. You can learn more about Michael’s work at his website and by following him on Twitter.