Evolving large-scale neural networks for vision-based TORCS

@inproceedings{Koutnk2013EvolvingLN,
  title={Evolving large-scale neural networks for vision-based TORCS},
  author={Jan Koutn{\'i}k and Giuseppe Cuccu and J{\"u}rgen Schmidhuber and Faustino J. Gomez},
  booktitle={FDG},
  year={2013}
}
The TORCS racing simulator has become a standard testbed used in many recent reinforcement learning competitions, where an agent must learn to drive a car around a track using a small set of task-specific features. In this paper, large, recurrent neural networks (with over 1 million weights) are evolved to solve a much more challenging version of the task that instead uses only a stream of images from the driver’s perspective as input. Evolving such large nets is made possible by representing… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 17 references

and J

  • D. Loiacono, P. L. Lanzi, +8 authors M. Preuss
  • Quadflieg. The 2009 simulated car racing…
  • 2009
1 Excerpt

celerated neural evolution through cooperatively coevolved synapses

  • R. Miikkulainen
  • Journal of Machine Learning Research
  • 2008

Similar Papers

Loading similar papers…