Learn to swing up and balance a real pole based on raw visual input data

Authors:
Jan Mattner;Sascha Lange;Martin Riedmiller
Affiliations:
Machine Learning Lab, Department of Computer Science, University of Freiburg, Freiburg, Germany;Machine Learning Lab, Department of Computer Science, University of Freiburg, Freiburg, Germany;Machine Learning Lab, Department of Computer Science, University of Freiburg, Freiburg, Germany
Venue:
ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part V
Year:
2012

Citing 4
Cited 0

Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Kernel-Based Reinforcement Learning

Machine Learning
Deep, big, simple neural nets for handwritten digit recognition

Neural Computation
Neural fitted q iteration – first experiences with a data efficient neural reinforcement learning method

ECML'05 Proceedings of the 16th European conference on Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

For the challenging pole balancing task we propose a system which uses raw visual input data for reinforcement learning to evolve a control strategy. Therefore we use a neural network --- a deep autoencoder --- to encode the camera images and thus the system states in a low dimensional feature space. The system is compared to controllers that work directly on the motor sensor data. We show that the performances of both systems are settled in the same order of magnitude.