video1.0<iframe src="https://www.loom.com/embed/48bc894db05a4a29aab04cda1255e070" frameborder="0" width="2560" height="1920" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>19202560Loomhttps://www.loom.com19202560https://cdn.loom.com/sessions/thumbnails/48bc894db05a4a29aab04cda1255e070-1702650329481.gif1617AI-driven multiphysics solvers, based on multi-agent reinforcement learning (MARL). This video from an invited talk at ICML 2022, and a longer version is available from Cambridge ML journal club: https://drive.google.com/file/d/1EsdkEN1htCZsUSv2asPf90lvoQTWE9V8/view?usp=drive_link