# Using Unity to Help Solve Intelligence

arXiv: https://arxiv.org/abs/2011.09294 · HTML: https://mlsanity.com/paper/2011.09294/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2020.

## Built on by (most cited first, 13 of 13)

- [Scaling Instructable Agents Across Many Simulated Worlds](https://mlsanity.com/paper/2404.10179/) (2024)
- [Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning](https://mlsanity.com/paper/2112.03763/) (2021)
- [A Review of Nine Physics Engines for Reinforcement Learning Research](https://mlsanity.com/paper/2407.08590/) (2024)
- [Learning Robust Real-Time Cultural Transmission without Human Data](https://mlsanity.com/paper/2203.00715/) (2022)
- [IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents](https://mlsanity.com/paper/2206.00142/) (2022)
- [Explainability Via Causal Self-Talk](https://mlsanity.com/paper/2211.09937/) (2022)
- [Dynamic Collaborative Multi-Agent Reinforcement Learning Communication for Autonomous Drone Reforestation](https://mlsanity.com/paper/2211.15414/) (2022)
- [Collaborative Auto-Curricula Multi-Agent Reinforcement Learning with Graph Neural Network Communication Layer for Open-ended Wildfire-Management Resource Distribution](https://mlsanity.com/paper/2204.11350/) (2022)
- [Hierarchical reinforcement learning with natural language subgoals](https://mlsanity.com/paper/2309.11564/) (2023)
- [The Animal-AI Environment: A Virtual Laboratory For Comparative Cognition and Artificial Intelligence Research](https://mlsanity.com/paper/2312.11414/) (2023)
- [NiceWebRL: a Python library for human subject experiments with reinforcement learning environments](https://mlsanity.com/paper/2508.15693/) (2025)
- [Hierarchical Reinforcement Learning in Complex 3D Environments](https://mlsanity.com/paper/2302.14451/) (2023)
- [Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies](https://mlsanity.com/paper/2606.10371/) (2026)

## Abstract (arXiv)

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.