Unity: A General Platform for Intelligent Agents

TL;DR

This paper advocates for using modern game engines, specifically Unity, as versatile platforms for developing complex, realistic, and configurable environments to advance artificial intelligence research.

Contribution

It introduces a taxonomy of simulation platforms, highlights Unity as a prime example, and discusses how such platforms enable diverse AI research.

Findings

Unity supports complex visual and physical simulations.

The Unity ML-Agents Toolkit facilitates diverse AI experiments.

Flexible simulation environments accelerate AI research.

Abstract

Recent advances in artificial intelligence have been driven by the presence of increasingly realistic and complex simulated environments. However, many of the existing environments provide either unrealistic visuals, inaccurate physics, low task complexity, restricted agent perspective, or a limited capacity for interaction among artificial agents. Furthermore, many platforms lack the ability to flexibly configure the simulation, making the simulated environment a black-box from the perspective of the learning system. In this work, we propose a novel taxonomy of existing simulation platforms and discuss the highest level class of general platforms which enable the development of learning environments that are rich in visual, physical, task, and social complexity. We argue that modern game engines are uniquely suited to act as general platforms and as a case study examine the Unity engine and open source Unity ML-Agents Toolkit. We then survey the research enabled by Unity and the Unity ML-Agents Toolkit, discussing the kinds of research a flexible, interactive and easily configurable general platform can facilitate.