Intersections between Control, Learning and Optimization 2020
“Learning Control from Minimal Prior Knowledge”
Martin Riedmiller – DeepMind Technologies
Abstract: Being able to autonomously learn control with minimal prior knowledge is a key ability of intelligent systems. This has therefore always been a central focus in our research on neural reinforcement learning methods. A particular challenge in real world control scenarios are methods that are at the same time highly data-efficient and robust, since data-collection on real systems is time intensive and often expensive. I will discuss two main research areas that are crucial for progress towards this goal: highly efficient off-policy learning and effective exploration. I will give examples of learning agent designs that can learn increasingly complex tasks from scratch in simulation and reality.
Institute for Pure and Applied Mathematics, UCLA
February 25, 2020
For more information: http://www.ipam.ucla.edu/lco2020
source