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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Voudouris, Konstantinos, Alhas, Ibrahim, Schellaert, Wout, Mecattaf, Matteo G., Slater, Ben, Crosby, Matthew, Holmes, Joel, Burden, John, Chaubey, Niharika, Donnelly, Niall, Patel, Matishalin, Halina, Marta, Hernández-Orallo, José, Cheke, Lucy G.
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913654796976128
author Voudouris, Konstantinos
Alhas, Ibrahim
Schellaert, Wout
Mecattaf, Matteo G.
Slater, Ben
Crosby, Matthew
Holmes, Joel
Burden, John
Chaubey, Niharika
Donnelly, Niall
Patel, Matishalin
Halina, Marta
Hernández-Orallo, José
Cheke, Lucy G.
author_facet Voudouris, Konstantinos
Alhas, Ibrahim
Schellaert, Wout
Mecattaf, Matteo G.
Slater, Ben
Crosby, Matthew
Holmes, Joel
Burden, John
Chaubey, Niharika
Donnelly, Niall
Patel, Matishalin
Halina, Marta
Hernández-Orallo, José
Cheke, Lucy G.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2312_11414
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle The Animal-AI Environment: A Virtual Laboratory For Comparative Cognition and Artificial Intelligence Research
Voudouris, Konstantinos
Alhas, Ibrahim
Schellaert, Wout
Mecattaf, Matteo G.
Slater, Ben
Crosby, Matthew
Holmes, Joel
Burden, John
Chaubey, Niharika
Donnelly, Niall
Patel, Matishalin
Halina, Marta
Hernández-Orallo, José
Cheke, Lucy G.
Artificial Intelligence
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.
title The Animal-AI Environment: A Virtual Laboratory For Comparative Cognition and Artificial Intelligence Research
topic Artificial Intelligence
url https://arxiv.org/abs/2312.11414