This course provides an overview and introduces modern methods for reinforcement learning (RL.) The course starts with the fundamentals of RL, such as Q-learning, and delves into commonly used approaches, like PPO and DQN. The course will introduce student ...
The goal of the summer school are providing a rigorous introduction to the foundations of MARL and highlight the challenges that arise in the modern research directions in this area. ...
Animals must learn from past experiences, to adapt their behavior to an ever-changing environment. Students will learn about the neuronal circuit mechanisms of reward-based learning, and of aversively-mediated learning, by studying the current scientific l ...
This course provides an overview of the theory of asset pricing and portfolio choice theory following historical developments in the field and putting
emphasis on theoretical models that help our understanding of financial decision
making and financial mar ...
Surprise, Reward, and Curiosity are drives of human, animal, and robot behavior. The class links theories of reinforcement learning with human behavior beyond standard notions of reward. ...
The Loss Landscape of Neural Networks is in general non-convex and rough, but recent mathematical results lead provide insights of practical relevance.
9 online lectures, lecturers from NYU, Stanford, Shanghai, IST Austria, Google, Facebook, EPFL. ...
This studio explores the meaningful generation of architectures by the use of artificial intelligence/deep learning and parametric tools and introduces the notion of the digital vernacular in architectural and urban design thinking. ...
The student will engage in a laboratory-based project in the field of computational neuroscience in one of the research labs of the EPFL working in this field. ...
The studio is conceived as an investigation into the archetypical elements of architecture in light of the challenges of our present age. By imbricating these two issues a framework is set up in which a critical reflection on what architecture might be tod ...