9 Computer Vision News Learning to take decisions The question of whether learning should be done from demonstrations through imitation learning, or from reward with reinforcement learning (RL), was hotly debated with several speakers suggesting that RL should be avoided whenever possible due to its difficulty. While there seemed to be a consensus that imitation learning seems to be an easier learning problem, enabling learning for a large variety of problems, RL was also shown to be the method of choice in several successful cases. Davide Scaramuzza, Professor at the University of Zürich (ETH), presented a spectacular success case, where RL was used to beat world champions in drone racing from first person views. Trained in simulation combined with recorded trajectories from real drones, this work, combining seven years of research of his group also showed that RL can beat optimal control for this task: whereas optimal control decomposes the problem into planning and control, limiting the range of behaviors, RL can directly optimize a task level objective and also cope with model uncertainty. RL was also the method of choice presented by Olivier Sigaud, Professor at Sorbonne University, who insisted on social aspects in particular in situations where artificial agents are either teachers or students, in which case they require pedagogical teaching capabilities or pragmatic interpretation capabilities, respectively. Davide Scaramuzza (ETH Zürich) on how RL beats optimal control for drone racing from first person views. at NAVER LABS Europe in Grenoble
RkJQdWJsaXNoZXIy NTc3NzU=