Events

CILVR Seminar: Learning complex robotic behaviors with optimal control

Speaker: Ludovic Righetti

Location: 60 Fifth Avenue, Room 7th floor open space
Videoconference link: https://nyu.zoom.us/s/92396384555

Date: Wednesday, October 1, 2025

Model-predictive control (MPC) and reinforcement learning (RL) have successfully been used to generate complex robotics behaviors, from flying robots to humanoids. While in principle they can both solve the same optimal control problems, their real-world performance can differ dramatically across tasks. In this talk, I will revisit the sometimes surprising optimization principles underlying these methods and argue for the benefits of “textbook” numerical optimization for designing reliable solvers. Throughout the talk, our recent results at the intersection of MPC, RL and world-model learning for a variety of legged locomotion and manipulation tasks will illustrate these claims. In particular, I will argue that as learned models become more complex, optimization algorithms need to increase in simplicity and I will point to existing challenges at the intersection of data and computational efficiency and scalability.