I am interested in ways to use reinforcement learning (RL) to train generally capable agents. I believe this will be made possible with an open-ended learning process, where environments constantly propose new challenges [1, 2] and agents adapt their configurations to solve them [3, 4, 5]. To make this process unbounded, I am excited by methods to actively encourage diversity [8, 9], while I believe we can eventually use world models to learn simulators purely from offline data [10, 11].