Using Unity to Help Solve Intelligence
This work provides a more versatile and robust platform for researchers to evaluate and develop artificial general intelligence agents, particularly in reinforcement learning, by overcoming the limitations of existing, constrained simulation environments.
This paper addresses the limitation of existing platforms for evaluating artificial general intelligence agents by using the Unity game engine to create more diverse and complex virtual simulation environments. It introduces concepts and components to simplify environment authoring, primarily for reinforcement learning, and a method for packaging and redistributing environments to improve experimental robustness and reproducibility.
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.