AI RESEARCH
Preemptive Solving of Future Problems: Multitask Preplay in Humans and Machines
arXiv CS.LG
•
ArXi:2507.05561v2 Announce Type: replace Humans can pursue a near-infinite variety of tasks, but typically can only pursue a small number at the same time. We hypothesize that humans leverage experience on one task to preemptively learn solutions to other tasks that were accessible but not pursued. We formalize this idea as Multitask Preplay, a novel algorithm that replays experience on one task as the starting point for "preplay" -- counterfactual simulation of an accessible but unpursued task.