Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer Architecture
Neural and Evolutionary Computing
2020-06-04 v2 Artificial Intelligence
Machine Learning
Machine Learning
Abstract
A key feature of intelligent behavior is the ability to learn abstract strategies that transfer to unfamiliar problems. Therefore, we present a novel architecture, based on memory-augmented networks, that is inspired by the von Neumann and Harvard architectures of modern computers. This architecture enables the learning of abstract algorithmic solutions via Evolution Strategies in a reinforcement learning setting. Applied to Sokoban, sliding block puzzle and robotic manipulation tasks, we show that the architecture can learn algorithmic solutions with strong generalization and abstraction: scaling to arbitrary task configurations and complexities, and being independent of both the data representation and the task domain.
Cite
@article{arxiv.1911.00926,
title = {Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer Architecture},
author = {Daniel Tanneberg and Elmar Rueckert and Jan Peters},
journal= {arXiv preprint arXiv:1911.00926},
year = {2020}
}