A Perspective on Objects and Systematic Generalization in Model-Based RL
Machine Learning
2019-06-05 v1 Artificial Intelligence
Neural and Evolutionary Computing
Machine Learning
Abstract
In order to meet the diverse challenges in solving many real-world problems, an intelligent agent has to be able to dynamically construct a model of its environment. Objects facilitate the modular reuse of prior knowledge and the combinatorial construction of such models. In this work, we argue that dynamically bound features (objects) do not simply emerge in connectionist models of the world. We identify several requirements that need to be fulfilled in overcoming this limitation and highlight corresponding inductive biases.
Cite
@article{arxiv.1906.01035,
title = {A Perspective on Objects and Systematic Generalization in Model-Based RL},
author = {Sjoerd van Steenkiste and Klaus Greff and Jürgen Schmidhuber},
journal= {arXiv preprint arXiv:1906.01035},
year = {2019}
}
Comments
Accepted to the ICML 2019 workshop on Workshop on Generative Modeling and Model-Based Reasoning for Robotics and AI