Fabian Ruehle | Machine Learning and Computational Complexity of String Theory Problems

Watch Fabian Ruehle's talk during the First French-German Meeting in Physics, Mathematics and Artificial Intelligence Theory that took place from November 4 to 6, 2019 in Paris. Abstract: I will start with an introductory review of string theory and the (mathematical and physical) challenges that come with it. I will then discuss the complexity classes of these problems and finally illustrate how we used reinforcement learning to find solutions for one class of string theory models. The reinforcement learning agent discovers solution strategies that have previously been employed by humans, but also discovers new, previously unknown strategies. _____ Follow us on: LinkedIn: https://www.linkedin.com/company/cealist Twitter: https://twitter.com/CEA_List Website: http://www-list.cea.fr/en