Efficient Action Representation for Robot Learning

Explore efficient action representation techniques for robot learning in this 55-minute talk by Samuele Tosatto, Assistant Professor at the Universitat Innsbruck. Delve into Tosatto's research on providing helpful representations and abstractions for embodied agents, as well as theoretical aspects of reinforcement learning to increase efficiency. Gain insights from his extensive academic background, including his postdoctoral work at the University of Alberta, PhD from Technische Universitat Darmstadt, and degrees from the Polytechnic University of Milan. Discover how these advanced concepts can enhance the learning capabilities of robotic systems and contribute to the field of robotics and artificial intelligence.

Samuele Tosatto: Efficient Action Representation for Robot Learning