Intrinsically motivated neuroevolution for vision-based reinforcement learning

@article{Cuccu2011IntrinsicallyMN,
  title={Intrinsically motivated neuroevolution for vision-based reinforcement learning},
  author={Giuseppe Cuccu and Matthew Luciw and J{\"u}rgen Schmidhuber and F. J. Rivera Gomez},
  journal={2011 IEEE International Conference on Development and Learning (ICDL)},
  year={2011},
  volume={2},
  pages={1-7}
}
Neuroevolution, the artificial evolution of neural networks, has shown great promise on continuous reinforcement learning tasks that require memory. However, it is not yet directly applicable to realistic embedded agents using high-dimensional (e.g. raw video images) inputs, requiring very large networks. In this paper, neuroevolution is combined with an unsupervised sensory pre-processor or compressor that is trained on images generated from the environment by the population of evolving… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 14 CITATIONS

Similar Papers

Loading similar papers…