The Animal-AI Testbed and Competition

Matthew Crosby, Benjamin Beyret, Murray Shanahan, José Hernández-Orallo, Lucy Cheke, Marta Halina
; Proceedings of the NeurIPS 2019 Competition and Demonstration Track, PMLR 123:164-176, 2020.

Abstract

Modern machine learning systems are still lacking in the kind of general intelligence and common sense reasoning found, not only in humans, but across the animal kingdom. Many animals are capable of solving seemingly simple tasks such as inferring object location through object persistence and spatial elimination, and navigating efficiently in out-of-distribution novel environments. Such tasks are difficult for AI, but provide a natural stepping stone towards the goal of more complex human-like general intelligence. The extensive literature on animal cognition provides methodology and experimental paradigms for testing such abilities but, so far, these experiments have not been translated en masse into an AI-friendly setting. We present a new testbed, Animal-AI, first released as part of the Animal-AI Olympics competition at NeurIPS 2019, which is a comprehensive environment and testing paradigm for tasks inspired by animal cognition. In this paper we outline the environment, the testbed, the results of the competition, and discuss the open challenges for building and testing artificial agents capable of the kind of nonverbal common sense reasoning found in many non-human animals.

Cite this Paper


BibTeX
@InProceedings{pmlr-v123-crosby20a, title = {The Animal-AI Testbed and Competition}, author = {Crosby, Matthew and Beyret, Benjamin and Shanahan, Murray and Hern\'{a}ndez-Orallo, Jos\'{e} and Cheke, Lucy and Halina, Marta}, pages = {164--176}, year = {2020}, editor = {Hugo Jair Escalante and Raia Hadsell}, volume = {123}, series = {Proceedings of Machine Learning Research}, address = {Vancouver, CA}, month = {08--14 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v123/crosby20a/crosby20a.pdf}, url = {http://proceedings.mlr.press/v123/crosby20a.html}, abstract = {Modern machine learning systems are still lacking in the kind of general intelligence and common sense reasoning found, not only in humans, but across the animal kingdom. Many animals are capable of solving seemingly simple tasks such as inferring object location through object persistence and spatial elimination, and navigating efficiently in out-of-distribution novel environments. Such tasks are difficult for AI, but provide a natural stepping stone towards the goal of more complex human-like general intelligence. The extensive literature on animal cognition provides methodology and experimental paradigms for testing such abilities but, so far, these experiments have not been translated en masse into an AI-friendly setting. We present a new testbed, Animal-AI, first released as part of the Animal-AI Olympics competition at NeurIPS 2019, which is a comprehensive environment and testing paradigm for tasks inspired by animal cognition. In this paper we outline the environment, the testbed, the results of the competition, and discuss the open challenges for building and testing artificial agents capable of the kind of nonverbal common sense reasoning found in many non-human animals.} }
Endnote
%0 Conference Paper %T The Animal-AI Testbed and Competition %A Matthew Crosby %A Benjamin Beyret %A Murray Shanahan %A José Hernández-Orallo %A Lucy Cheke %A Marta Halina %B Proceedings of the NeurIPS 2019 Competition and Demonstration Track %C Proceedings of Machine Learning Research %D 2020 %E Hugo Jair Escalante %E Raia Hadsell %F pmlr-v123-crosby20a %I PMLR %J Proceedings of Machine Learning Research %P 164--176 %U http://proceedings.mlr.press %V 123 %W PMLR %X Modern machine learning systems are still lacking in the kind of general intelligence and common sense reasoning found, not only in humans, but across the animal kingdom. Many animals are capable of solving seemingly simple tasks such as inferring object location through object persistence and spatial elimination, and navigating efficiently in out-of-distribution novel environments. Such tasks are difficult for AI, but provide a natural stepping stone towards the goal of more complex human-like general intelligence. The extensive literature on animal cognition provides methodology and experimental paradigms for testing such abilities but, so far, these experiments have not been translated en masse into an AI-friendly setting. We present a new testbed, Animal-AI, first released as part of the Animal-AI Olympics competition at NeurIPS 2019, which is a comprehensive environment and testing paradigm for tasks inspired by animal cognition. In this paper we outline the environment, the testbed, the results of the competition, and discuss the open challenges for building and testing artificial agents capable of the kind of nonverbal common sense reasoning found in many non-human animals.
APA
Crosby, M., Beyret, B., Shanahan, M., Hernández-Orallo, J., Cheke, L. & Halina, M.. (2020). The Animal-AI Testbed and Competition. Proceedings of the NeurIPS 2019 Competition and Demonstration Track, in PMLR 123:164-176

Related Material