Recorded 24 September 2024. Kelsey Allen of DeepMind presents "Physical problem-solving across timescales" at IPAM's Analyzing High-dimensional Traces of Intelligent Behavior Workshop. Abstract: Every human culture we know of creates and re-purposes objects as tools to achieve their goals and shape the environment in useful ways. These capabilities come so easily to us that we often forget how complex these behaviors are. Despite the universality of tool use in people, only a handful of other animals use objects in this way, and we tend to think of these as some of the most intelligent behaviors that other species display. In this talk, I will discuss my research program aiming to illuminate the computational and cognitive foundations of this kind of flexible physical problem-solving across multiple timescales of experience. By combining perspectives from cognitive science, machine learning, and robotics, my research suggests that the flexibility and efficiency of human physical problem-solving is supported by combining structured knowledge with learning, rather than choosing one or the other. To explain human flexibility, actions must be structured in relational, object-oriented ways. To explain human efficiency, mental simulation in the form of intuitive physics is critical, as relational actions alone are not enough. With these structures in place, learning guides how we search through and adapt our actions over multiple timescales -- either over just a few attempts within a problem, over related problems with shared relational structure, or over a lifetime of embodied experience. Learn more online at: https://www.ipam.ucla.edu/programs/workshops/workshop-i-analyzing-high-dimensional-traces-of-intelligent-behavior/?tab=overview