Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Direct Human-AI Comparison in the Animal-AI Environment

  • Voudouris, Konstantinos
  • Crosby, Matthew
  • Beyret, Benjamin
  • Shanahan, Murray
  • Halina, Marta
  • Cheke, Lucy G.
  • Hernández-Orallo, José|||0000-0001-9746-7632
[EN] Artificial Intelligence is making rapid and remarkable progress in the development of more sophisticated and powerful systems. However, the acknowledgement of several problems with modern machine learning approaches has prompted a shift in AI benchmarking away from task-oriented testing (such as Chess and Go) towards ability-oriented testing, in which AI systems are tested on their capacity to solve certain kinds of novel problems. The Animal-AI Environment is one such benchmark which aims to apply the ability-oriented testing used in comparative psychology to AI systems. Here, we present the first direct human-AI comparison in the Animal-AI Environment, using children aged 6-10 (n = 52). We found that children of all ages were significantly better than a sample of 30 AIs across most of the tests we examined, as well as performing significantly better than the two top-scoring AIs, "ironbar" and "Trrrrr," from the Animal-AI Olympics Competition 2019. While children and AIs performed similarly on basic navigational tasks, AIs performed significantly worse in more complex cognitive tests, including detour tasks, spatial elimination tasks, and object permanence tasks, indicating that AIs lack several cognitive abilities that children aged 6-10 possess. Both children and AIs performed poorly on tool-use tasks, suggesting that these tests are challenging for both biological and non-biological machines., This work was supported by ESRC DTP funding to KV, ESRC award reference: ES/P000738/1. Research was conducted as a project within the Kinds of Intelligence Program at the Leverhulme Centre for the Future of Intelligence, award number: G108086, and the US DARPA HR00112120007 (RECoG-AI) Grant.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

The Animal-AI Environment: A virtual laboratory for comparative cognition and artificial intelligence research

  • Voudouris, Konstantinos
  • Slater, Ben
  • Cheke, Lucy G.
  • Schellaert, Wout Willy M.
  • Halina, Marta
  • Patel, Matishalin
  • Alhas, Ibrahim
  • Mecattaf, Matteo G.
  • Burden, John
  • Holmes, Joel
  • Chaubey, Niharika
  • Donnelly, Niall
  • Crosby, Matthew
  • Hernández-Orallo, José|||0000-0001-9746-7632
[EN] 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., This work was funded by an ESRC DTP scholarship (ES/P000 738/1), the Kinds of Intelligence Program at the Leverhulme Centre for the Future of Intelligence (G108086), the US DARPA HR00112120007 (RECoG-AI) grant, and a Templeton World Charity Foundation grant (Major Transitions in the Evolution of Cognition: TWCF-2020- 20539). This work was also funded by the European Union with the "Programa Operativo del Fondo Europeo de Desarrollo Regional (FEDER) de la Comunitat Valenciana 2014-2020" under agreement INNEST/2021/317 (Neurocalcat) and by the Vic. Inv. of the Universitat Politecnica de Valencia under "programa de ayudas a la formacion de doctores en colaboracion con empresas" (DOCEMPR21).