The Animal-AI Environment: A Virtual Laboratory For Comparative Cognition and Artificial Intelligence Research

TL;DR

The Animal-AI Environment is a versatile virtual platform designed to advance research in comparative cognition and AI by providing complex, engaging tasks that facilitate collaboration and testing of AI systems against biological cognition models.

Contribution

This paper introduces an upgraded Animal-AI Environment with enhanced features and detailed experimental guidance, enabling more effective testing of AI and biological cognition.

Findings

Deep reinforcement learning agents like Dreamer-v3 perform well on new tasks

The environment improves training efficiency and user experience

It offers a biologically inspired framework for AI and cognition research

Abstract

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.