mlsanityData to 14 Oct 2026

Unity: A General Platform for Intelligent Agents

arXiv 1809.02627 ↗First posted 7 Sep 2018cs.LG cs.AI cs.NEcited by 236

Not on the map. Why?

Cited by 27 in Deep reinforcement learning methods, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

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.

Key facts. Cited by 236 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 43; 2022: 54; 2023: 51; 2024: 32; 2025: 33; 2026: 22.

236 papers.

Sort:

By area:

  1. 2023AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedbackcited by 748
  2. 2021Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulationcited by 407
  3. 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 327
  4. 2023Habitat 3.0: A Co-Habitat for Humans, Avatars and Robotscited by 228
  5. 2021Benchmarking the Spectrum of Agent Capabilitiescited by 200
  6. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 179
  7. 2022TransDreamer: Reinforcement Learning with Transformer World Modelscited by 143
  8. 2022COUCH: Towards Controllable Human-Chair Interactionscited by 135
  9. 2021Learning High-Speed Flight in the Wildcited by 128
  10. 2024A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlookcited by 66
  11. 2023Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAXcited by 58
  12. 2023Lyfe Agents: Generative agents for low-cost real-time social interactionscited by 49
38 more
  1. 2025AutoEval: Autonomous Evaluation of Generalist Robot Manipulation Policies in the Real Worldcited by 48
  2. 2024CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agentscited by 42
  3. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Reviewcited by 38
  4. 2021Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agentscited by 36
  5. 2021Adversarial Reinforcement Learning for Procedural Content Generationcited by 36
  6. 20243D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucinationcited by 36
  7. 2022Verifying Learning-Based Robotic Navigation Systemscited by 33
  8. 20213DB: A Framework for Debugging Computer Vision Modelscited by 31
  9. 2024A Survey of Small Language Modelscited by 31
  10. 2021The 5th AI City Challengecited by 28
  11. 2025A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectivescited by 27
  12. 2023GINA-3D: Learning to Generate Implicit Neural Assets in the Wildcited by 25
  13. 2021NViSII: A Scriptable Tool for Photorealistic Image Generationcited by 24
  14. 2021When Pigs Fly: Contextual Reasoning in Synthetic and Natural Scenescited by 23
  15. 2022The 6th AI City Challengecited by 23
  16. 2022A Survey and Framework of Cooperative Perception: From Heterogeneous Singleton to Hierarchical Cooperationcited by 21
  17. 2022Transfer RL across Observation Feature Spaces via Model-Based Regularizationcited by 18
  18. 2022Ask4Help: Learning to Leverage an Expert for Embodied Taskscited by 18
  19. 2021The Neural MMO Platform for Massively Multiagent Researchcited by 17
  20. 2022Hybrid Reinforcement Learning-Based Eco-Driving Strategy for Connected and Automated Vehicles at Signalized Intersectionscited by 16
  21. 2024The 3D-PC: a benchmark for visual perspective taking in humans and machinescited by 16
  22. 2020Benchmarking End-to-End Behavioural Cloning on Video Gamescited by 15
  23. 2022CLIP meets GamePhysics: Towards bug identification in gameplay videos using zero-shot transfer learningcited by 15
  24. 2023Games for Artificial Intelligence Research: A Review and Perspectivescited by 14
  25. 2023Adaptive Coordination in Social Embodied Rearrangementcited by 14
  26. 2024Gaussian Splatting to Real World Flight Navigation Transfer with Liquid Networkscited by 14
  27. 2021Verifiable and Compositional Reinforcement Learning Systemscited by 13
  28. 2022Learning to Generalize with Object-centric Agents in the Open World Survival Game Craftercited by 13
  29. 2022A System for Morphology-Task Generalization via Unified Representation and Behavior Distillationcited by 13
  30. 2023A Domain-Agnostic Approach for Characterization of Lifelong Learning Systemscited by 13
  31. 2023Inferring Capabilities from Task Performance with Bayesian Triangulationcited by 13
  32. 2023UniFolding: Towards Sample-efficient, Scalable, and Generalizable Robotic Garment Foldingcited by 13
  33. 2022A Survey on Reinforcement Learning Methods in Character Animationcited by 12
  34. 2024A Review of Nine Physics Engines for Reinforcement Learning Researchcited by 12
  35. 2021Curriculum Learning for Safe Mapless Navigationcited by 11
  36. 2022Constrained Reinforcement Learning for Robotics via Scenario-Based Programmingcited by 11
  37. 2022Automated Play-Testing Through RL Based Human-Like Play-Styles Generationcited by 11
  38. 2023Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Gamescited by 11

50 most cited of 236 All 236 (JSON)