1 code implementation • 25 Feb 2021 • Ravi Kumar Thakur, MD-Nazmus Samin Sunbeam, Vinicius G. Goecks, Ellen Novoseller, Ritwik Bera, Vernon J. Lawhern, Gregory M. Gremillion, John Valasek, Nicholas R. Waytowich
In this work, we propose Gaze Regularized Imitation Learning (GRIL), a novel context-aware, imitation learning architecture that learns concurrently from both human demonstrations and eye gaze to solve tasks where visual attention provides important context.
no code implementations • 1 Nov 2019 • Ritwik Bera, Vinicius G. Goecks, Gregory M. Gremillion, John Valasek, Nicholas R. Waytowich
Learning from demonstration has been widely studied in machine learning but becomes challenging when the demonstrated trajectories are unstructured and follow different objectives.
no code implementations • 9 Oct 2019 • Vinicius G. Goecks, Gregory M. Gremillion, Vernon J. Lawhern, John Valasek, Nicholas R. Waytowich
However, it is currently unclear how to efficiently update that policy using reinforcement learning as these approaches are inherently optimizing different objective functions.
1 code implementation • 26 Oct 2018 • Vinicius G. Goecks, Gregory M. Gremillion, Vernon J. Lawhern, John Valasek, Nicholas R. Waytowich
This paper investigates how to utilize different forms of human interaction to safely train autonomous systems in real-time by learning from both human demonstrations and interventions.