Intrinsically motivated neuroevolution for vision-based reinforcement learning

Giuseppe Cuccu, Matthew Luciw, Jürgen Schmidhuber, Faustino Gomez

Research output: Chapter in Book/Report/Conference proceedingConference contribution

22 Scopus citations


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 recurrent neural network controllers. The compressor not only reduces the input cardinality of the controllers, but also biases the search toward novel controllers by rewarding those controllers that discover images that it reconstructs poorly. The method is successfully demonstrated on a vision-based version of the well-known mountain car benchmark, where controllers receive only single high-dimensional visual images of the environment, from a third-person perspective, instead of the standard two-dimensional state vector which includes information about velocity. © 2011 IEEE.
Original languageEnglish (US)
Title of host publication2011 IEEE International Conference on Development and Learning, ICDL 2011
StatePublished - Nov 1 2011
Externally publishedYes


Dive into the research topics of 'Intrinsically motivated neuroevolution for vision-based reinforcement learning'. Together they form a unique fingerprint.

Cite this