Description
14:00
Extracting Strong Policies for Robotics Tasks from Zero-Order Trajectory Optimizers
Sebastian Blaes, Cristina Pinneri and Georg Martius
14:12
Specializing Versatile Skill Libraries using Local Mixture of Experts
Mevlüt Onur Celik, Dongzhuoran Zhou, Ge Li, Philipp Becker and Gerhard Neumann
14:24
Combining Manipulation Primitive Nets and Policy Gradient Methods for Learning Robotic Assembly Tasks
Marco Braun and Sebastian Wrede
14:36
Robot Dynamics Learning with Action Conditional Recurrent Kalman Networks
Vaisakh Shaj, Philipp Becker and Gerhard Neumann
14:48
Seamless Sequencing of Skills via Differentiable Optimization
Noémie Jaquier, Julia Starke, You Zhou and Tamim Asfour
15:00
Learning Control Policies from Optimal Trajectories
Christoph Zelch, Jan Peters and Oskar von Stryk
