Anurag Ajay

My research goal is to design algorithms that can enable agents to continuously interact, learn, and perform complex tasks in their environments. To this end, I am interested in learning Visuomotor Priors for Behavior Transfer: leveraging past interactions to learn both visual and control priors that allows agent to quickly adapt to new environments.

In the past, I have worked on using deep learning for state estimation, building model-based deep reinforcement learning algorithms for robotics and learning dynamics model, with the help of physics engines, in the robotics domain.