Using Unity to Help Solve Intelligence

TL;DR

This paper demonstrates how Unity game engine can be used to create diverse, complex virtual environments for evaluating artificial general intelligence, improving environment variety and reproducibility.

Contribution

It introduces a Unity-based framework for environment creation in reinforcement learning, enhancing diversity, complexity, and reproducibility of experimental setups.

Findings

Created multiple environments from published papers using Unity

Improved robustness and reproducibility of experiments

Showcased versatility of Unity in AI research environments

Abstract

In the pursuit of artificial general intelligence, our most significant measurement of progress is an agent's ability to achieve goals in a wide range of environments. Existing platforms for constructing such environments are typically constrained by the technologies they are founded on, and are therefore only able to provide a subset of scenarios necessary to evaluate progress. To overcome these shortcomings, we present our use of Unity, a widely recognized and comprehensive game engine, to create more diverse, complex, virtual simulations. We describe the concepts and components developed to simplify the authoring of these environments, intended for use predominantly in the field of reinforcement learning. We also introduce a practical approach to packaging and re-distributing environments in a way that attempts to improve the robustness and reproducibility of experiment results. To illustrate the versatility of our use of Unity compared to other solutions, we highlight environments already created using our approach from published papers. We hope that others can draw inspiration from how we adapted Unity to our needs, and anticipate increasingly varied and complex environments to emerge from our approach as familiarity grows.