Delta Schema Network in Model-based Reinforcement Learning
Machine Learning
2020-07-09 v2 Artificial Intelligence
Abstract
This work is devoted to unresolved problems of Artificial General Intelligence - the inefficiency of transfer learning. One of the mechanisms that are used to solve this problem in the area of reinforcement learning is a model-based approach. In the paper we are expanding the schema networks method which allows to extract the logical relationships between objects and actions from the environment data. We present algorithms for training a Delta Schema Network (DSN), predicting future states of the environment and planning actions that will lead to positive reward. DSN shows strong performance of transfer learning on the classic Atari game environment.
Cite
@article{arxiv.2006.09950,
title = {Delta Schema Network in Model-based Reinforcement Learning},
author = {Andrey Gorodetskiy and Alexandra Shlychkova and Aleksandr I. Panov},
journal= {arXiv preprint arXiv:2006.09950},
year = {2020}
}
Comments
Published at the AGI 2020 conference