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

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.

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 simulated car racing championship
  • 2009
1 Excerpt

celerated neural evolution through cooperatively coevolved synapses

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

Similar Papers

Loading similar papers…