Unsupervised state representation learning with robotic priors: a robustness benchmark

no code implementations • 15 Sep 2017 • Timothée Lesort, Mathieu Seurin, Xinrui Li, Natalia Díaz Rodríguez, David Filliat

We reproduce this simplification process using a neural network to build a low dimensional state representation of the world from images acquired by a robot.

Position Reinforcement Learning (RL) +2