Corpus ID: 232233391

Hybrid computer approach to train a machine learning system

@article{Holzer2021HybridCA,
  title={Hybrid computer approach to train a machine learning system},
  author={Mirko Holzer and B. Ulmann},
  journal={ArXiv},
  year={2021},
  volume={abs/2103.07802}
}
This chapter describes a novel approach to training machine learning systems by means of a hybrid computer setup i. e. a digital computer tightly coupled with an analog computer. In this example, a reinforcement learning system is trained to balance an inverted pendulum which is simulated on an analog computer, demonstrating a solution to the major challenge of adequately simulating the environment for reinforcement learning. 

Figures from this paper

References

SHOWING 1-6 OF 6 REFERENCES
Q-learning
  • 5,917
  • PDF
Learning from delayed rewards
  • B. Kröse
  • Computer Science
  • Robotics Auton. Syst.
  • 1995
  • 2,767
The master algorithm: how the quest for the ultimate learning machine will remake our world
  • 180
  • PDF
A few useful things to know about machine learning
  • 1,835
  • PDF
An Introduction to Lagrangian Mechanics
  • 51
  • PDF
Machine learning with Python
  • 657