2021/02/19 by Paula Gradu, Gradu, Paula, John Hallman +17 · 1 citation
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Robotics (cs.RO) #cs.LG #cs.RO
paper · pdf · doi:10.48550/arxiv.2102.09968
arxiv created 2021/02/19 · arxiv updated 2021/02/22
We present an open-source library of natively differentiable physics and robotics environments, accompanied by gradient-based control methods and a benchmark-ing suite. The introduced environments allow auto-differentiation through the simulation dynamics, and thereby permit fast training of controllers. The library features several popular environments, including classical control settings from OpenAI Gym. We also provide a novel differentiable environment, based on deep neural networks, that simulates medical ventilation. We give several use-cases of new scientific results obtained using the library. This includes a medical ventilator simulator and controller, an adaptive control method for time-varying linear dynamical systems, and new gradient-based methods for control of linear dynamical systems with adversarial perturbations.