2 papers
cs.LG2019
Dynamic Interaction-Aware Scene Understanding for Reinforcement Learning in Autonomous Driving
Maria Huegle, Gabriel Kalweit, Moritz Werling +1
The common pipeline in autonomous driving systems is highly modular and includes a perception component which extracts lists of surrounding objects and passes these lists to a high…
cs.LG2019
Composite Q-learning: Multi-scale Q-function Decomposition and Separable Optimization
Gabriel Kalweit, Maria Huegle, Joschka Boedecker
In the past few years, off-policy reinforcement learning methods have shown promising results in their application for robot control. Deep Q-learning, however, still suffers from p…