User: Guest  Login
Document type:
Konferenzbeitrag 
Author(s):
Oliva, Marco; Banik, Soubarna; Josifovski, Josip; Knoll, Alois 
Title:
Graph Neural Networks for Relational Inductive Bias in Vision-based Deep Reinforcement Learning of Robot Control 
Abstract:
State-of-the-art reinforcement learning algorithms predominantly learn a policy from either a numerical state vector or images. Both approaches generally do not take structural knowledge of the task into account, which is especially prevalent in robotic applications and can benefit learning if exploited. This work introduces a neural network architecture that combines relational inductive bias and visual feedback to learn an efficient position control policy for robotic manipulation. We derive a...    »
 
Keywords:
Graph neural networks, Reinforcement learning, Robot control, Inductive bias, Convolutional neural networks 
Book / Congress title:
IEEE Internatinal Joint Conference on Neural Networks 
Year:
2022