Taylor Howell — accepted AI-conference papers

2026

Whole-Body Model-Predictive Control of Legged Robots with MuJoCo

John Zhang, Taylor Howell, Zeji Yi, Chaoyi Pan, Guanya Shi, Guannan Qu +3

ICRA 2026poster

We demonstrate the surprising real-world effectiveness of a very simple approach to whole-body model- predictive control (MPC) of quadruped and humanoid robots: the iterative linear-quadratic regulator (iLQR) algorithm with MuJoCo dynamics and finite-difference approximated derivatives. Building upo…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

RoboPianist: Dexterous Piano Playing with Deep Reinforcement Learning

Kevin Zakka, Philipp Wu, Laura Smith, Nimrod Gileadi, Taylor Howell, Xue Bin Peng +5

CoRL 2023poster

Replicating human-like dexterity in robot hands represents one of the largest open problems in robotics. Reinforcement learning is a promising approach that has achieved impressive progress in the last few years; however, the class of problems it has typically addressed corresponds to a rather narro…

Cited by 47 Source ↗code ↗Scholar ↗