A Reinforcement Learning System for Generating Instantaneous Quality Random Sequences

Abstract

Random numbers are essential to most computer applications. Still, producing high-quality random sequences is a big challenge. Inspired by the success of artificial neural networks and reinforcement learning, we propose a novel and effective end-to-end learning system to generate pseudo-random sequences and operates under the upside-down reinforcement learning framework. It is based on manipulating the generalized information entropy metric to derive commands that instantaneously guide the agent towards the optimal random behaviour. Using a wide range of evaluation tests, the proposed approach is compared against three state-of-the-art accredited Pseudo-Random Number Generators (PRNGs). The experimental results agree with our theoretical study and show that the proposed framework is a promising candidate for a wide range of applications.