Reinforcement Learning Neural Turing Machines - Revised

TL;DR

This paper explores the use of reinforcement learning to train neural networks that interact with discrete external interfaces like memory and tapes, demonstrating Turing completeness for solving algorithmic tasks.

Contribution

It introduces a method for training neural networks to interact with discrete external interfaces using reinforcement learning, extending the capabilities of Neural Turing Machines.

Findings

Neural networks can learn to interact with discrete interfaces.

The model achieves Turing completeness with the proposed interfaces.

Reinforcement learning effectively trains models for algorithmic tasks.

Abstract

The Neural Turing Machine (NTM) is more expressive than all previously considered models because of its external memory. It can be viewed as a broader effort to use abstract external Interfaces and to learn a parametric model that interacts with them. The capabilities of a model can be extended by providing it with proper Interfaces that interact with the world. These external Interfaces include memory, a database, a search engine, or a piece of software such as a theorem verifier. Some of these Interfaces are provided by the developers of the model. However, many important existing Interfaces, such as databases and search engines, are discrete. We examine feasibility of learning models to interact with discrete Interfaces. We investigate the following discrete Interfaces: a memory Tape, an input Tape, and an output Tape. We use a Reinforcement Learning algorithm to train a neural network that interacts with such Interfaces to solve simple algorithmic tasks. Our Interfaces are expressive enough to make our model Turing complete.