I am Samuele Tosatto, an Assistant Professor at the University of Innsbruck, focusing on the intersection of reinforcement learning and robotics. Before joining the faculty here, I was a postdoctoral researcher at the RLAI Lab under the direction of Prof. Mahmood. I earned my Ph.D. at the Intelligent Autonomous System (IAS) lab, supervised by Prof. Jan Peters, where I defended my dissertation, “Towards Off-Policy Reinforcement Learning for Robotics.”
My current research goal is to develop embodied learning agents.
Embodied agents are real-world systems, like robots, that perceive and interact with the real world. Most of the current autonomous systems have limited intelligence and understanding of the world. I am interested in making those systems smarter and capable of learning by interacting with the real world.
Most current research focuses on training agents in a simulated environment and then transferring the learned behaviours into the real world.
While this approach simplifies many challenges in the real world (such as safety and sample complexity), it is hardly scalable, as it requires designing new virtual environments for different tasks! Furthermore, I believe that our ultimate goal should be to have robots that continuously learn in the world, just like we do!
To solve this challenge, I focus my research on reinforcement learning (a technique that allows agents to learn from a reward signal), representation learning for robotics (e.g., movement primitives), and learning abstraction.
I have a new position open! Check it out and apply!
For further questions, contact me via email: samuele.tosatto@uibk.ac.at