The Animal-AI Environment: A Virtual Laboratory For Comparative Cognition and Artificial Intelligence Research
Not on the map. Why?
Abstract (arXiv)
The Animal-AI Environment is a unique game-based research platform designed to facilitate collaboration between the artificial intelligence and comparative cognition research communities. In this paper, we present the latest version of the Animal-AI Environment, outlining several major features that make the game more engaging for humans and more complex for AI systems. These features include interactive buttons, reward dispensers, and player notifications, as well as an overhaul of the environment's graphics and processing for significant improvements in agent training time and quality of the human player experience. We provide detailed guidance on how to build computational and behavioural experiments with the Animal-AI Environment. We present results from a series of agents, including the state-of-the-art deep reinforcement learning agent Dreamer-v3, on newly designed tests and the Animal-AI Testbed of 900 tasks inspired by research in the field of comparative cognition. The Animal-AI Environment offers a new approach for modelling cognition in humans and non-human animals, and for building biologically inspired artificial intelligence.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 21 of its 91 references that are in the map. First posted on arXiv 18 Dec 2023.
Builds on
21 of 91 references.
References · 21
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
- 2023Mastering Diverse Domains through World Modelscited by 1,253
- 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 478
- 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 373
- 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 327
- 2020ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulationcited by 250
- 2018Unity: A General Platform for Intelligent Agentscited by 236
- 2023Human-Timescale Adaptation in an Open-Ended Task Spacecited by 138
- 2018Dopamine: A Research Framework for Deep Reinforcement Learningcited by 122
- 2021The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priorscited by 41
- 2018Investigating Human Priors for Playing Video Gamescited by 39
9 more
- 2022Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worldscited by 17
- 2019The Animal-AI Environment: Training and Testing Animal-Like Artificial Cognitioncited by 16
- 2018Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agentscited by 15
- 2020Using Unity to Help Solve Intelligencecited by 13
- 2023Inferring Capabilities from Task Performance with Bayesian Triangulationcited by 13
- 2021OPEn: An Open-ended Physics Environment for Learning Without a Taskcited by 4
- 2020crea.blender: A Neural Network-Based Image Generation Game to Assess Creativitycited by 3
- 2021Sequential memory improves sample and memory efficiency in Episodic Controlcited by 3
- 2021Fixed β-VAE Encoding for Curious Exploration in Complex 3D Environmentscited by 1
Built on by
Citing papers per year: 2026: 2.
2 papers.