publication . Conference object . 2014

evolving deep unsupervised convolutional networks for vision based reinforcement learning

Jan Koutník; Juergen Schmidhuber; Faustino Gomez;
Open Access
  • Published: 11 Jul 2014
  • Publisher: ACM Press
Abstract
Dealing with high-dimensional input spaces, like visual input, is a challenging task for reinforcement learning (RL). Neuroevolution (NE), used for continuous RL problems, has to either reduce the problem dimensionality by (1) compressing the representation of the neural network controllers or (2) employing a pre-processor (compressor) that transforms the high-dimensional raw inputs into low-dimensional features. In this paper, we are able to evolve extremely small recurrent neural network (RNN) controllers for a task that previously required networks with over a million weights. The high-dimensional visual input, which the controller would normally receive, is ...
Subjects
free text keywords: Recurrent neural network, Control theory, Feature vector, Reinforcement learning, Machine learning, computer.software_genre, computer, Artificial intelligence, business.industry, business, Convolutional neural network, Computer science, Neuroevolution, Deep learning, Artificial neural network
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue