CHAI Research on Self-Teaching AI Featured in Science

01 Mar 2021

A new article in Science, Who needs a teacher? Artificial intelligence designs lesson plans for itself, features two recent papers from members of CHAI.

The first paper, “Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design,” by Michael Dennis, Stuart Russell, and Andrew Critch, was presented in the Deep RL Workshop at NeurIPS 2020. The second paper, “A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances,” was also presented at NeurIPS 2020 and is co-authored by Prof. Bart Selman of Cornell University. Read more about their work in Science.