Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer

Sep 25, 2019 Blind Submission readers: everyone Show Bibtex
  • 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.
  • TL;DR: A novel neural computer architecture that learns transferable abstract strategies to symbolic planning tasks as algorithmic solutions with evolution strategies.
  • Original Pdf:  pdf
0 Replies

Loading