Sammendrag
How should we build machines that demonstrate human-like capabilities? I have been asking myself this question for a long time. It has put me on the path to exploring different paradigms in robotics and Artificial Intelligence (AI). With this motivation, I explored various topics in AI during my graduate and post-graduate studies at IIT Madras and TU Delft, and during my research internship at MPI-IS. Through my academic journey, Reinforcement Learning resonated with me and stood out as a plausible way for building systems to solve sequential decision-making problems, a relevant characteristic of intelligent machines. To that end, I am currently investigating Safe Reinforcement Learning and Model Predictive Control as a PhD researcher with Prof. Sebastien Gros at NTNU.
Vis fullstendig beskrivelse
