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
Highly Cited
This paper has 122 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 1 time over the past 90 days. VIEW TWEETS

Citations

Publications citing this paper.

122 Citations

0204020142015201620172018
Citations per Year
Semantic Scholar estimates that this publication has 122 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…