As the current trend of artificial intelligence is shifting towards self-supervised learning, conventional norms such as highly curated domain-specific data, application-specific learning models, extrinsic reward based learning policies etc. might not provide with the suitable ground for such developments. In this paper, we introduce SEDRo, a Simulated Environment for Developmental Robotics which allows a learning agent to have similar experiences that a human infant goes through from the fetus stage up to 12 months. A series of simulated tests based on developmental psychology will be used to evaluate the progress of a learning model.
@article{arxiv.2007.09300,
title = {An Open-World Simulated Environment for Developmental Robotics},
author = {SM Mazharul Islam and Md Ashaduzzaman Rubel Mondol and Aishwarya Pothula and Deokgun Park},
journal= {arXiv preprint arXiv:2007.09300},
year = {2020}
}
Comments
Presented at Workshop on Learning in Artificial Open Worlds held with ICML 2020