The ability to learn a model is essential for the success of autonomous agents. Unfortunately, learning a model is difficult in partially observable environments, where latent environmental factors influence what the agent observes. In the absence of a supervisory training signal, autonomous agents therefore require a mechanism to autonomously discover these environmental factors, or sensorimotor contexts. This paper presents a method to discover sensorimotor contexts in partially observable environments, by constructing a hierarchical transition model. The method is evaluated in a simulation experiment, in which a robot learns that different rooms are characterized by different objects that are found in them.
@article{arxiv.1608.00737,
title = {Context Discovery for Model Learning in Partially Observable Environments},
author = {Nikolas J. Hemion},
journal= {arXiv preprint arXiv:1608.00737},
year = {2016}
}
Comments
6th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (IEEE ICDL-EPIROB 2016)