Evolving large-scale neural networks for vision-based reinforcement learning

@inproceedings{Koutnk2013EvolvingLN,
  title={Evolving large-scale neural networks for vision-based reinforcement learning},
  author={Jan Koutn{\'i}k and Giuseppe Cuccu and J{\"u}rgen Schmidhuber and Faustino J. Gomez},
  booktitle={GECCO},
  year={2013}
}
The idea of using evolutionary computation to train artificial neural networks, or neuroevolution (NE), for reinforcement learning (RL) tasks has now been around for over 20 years. However, as RL tasks become more challenging, the networks required become larger, as do their genomes. But, scaling NE to large nets (i.e. tens of thousands of weights) is infeasible using direct encodings that map genes one-to-one to network components. In this paper, we scale-up our compressed network encoding… CONTINUE READING
Tweets
This paper has been referenced on Twitter 1 time. VIEW TWEETS

Citations

Publications citing this paper.
SHOWING 1-10 OF 68 CITATIONS, ESTIMATED 28% COVERAGE

FILTER CITATIONS BY YEAR

2014
2019

CITATION STATISTICS

  • 4 Highly Influenced Citations

  • Averaged 18 Citations per year over the last 3 years

Similar Papers

Loading similar papers…