Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture delves into the concept of learning strategies in robotics, focusing on the reward system for the outer and inner loops, the role of fixtures in training, and the process of removing scaffolds to enhance learning. It also discusses the generalization of training from simulation to the real world, emphasizing the importance of physical constraints and depth images. Additionally, the lecture explores the challenges of reaching unstable states in tasks and the impact of exploiting passive dynamics in learning, shedding light on the differences in individual learning approaches.