Michael DennisReal world environments are complicated, too complicated to be completely specified in any simulation or model. I research Problem Specification -- studying the boundary between what complexity must be described, and what can be artificially generated.
To this end we have formalized the problem of 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.
I am currently a final year PhD candidate at UC Berkeley's Center for Human Compatible AI(CHAI) advised by Stuart Russell. I also have an extensive background in computer science theory and computational geometry.