paper-with-me

홈 › Papers

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

2023-12-18 · Konstantinos Voudouris, Ibrahim Alhas, Wout Schellaert, Matteo G. Mecattaf, Ben Slater, Matthew Crosby, Joel Holmes, John Burden, Niharika Chaubey, Niall Donnelly, Matishalin Patel, Marta Halina, José Hernández-Orallo, Lucy G. Cheke

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.

📄 PDF Abstract BibTeX arXiv:2312.11414

Code (1)

kinds-of-intelligence-cfi/animal-ai 공식 구현 tf

Tasks

Deep Reinforcement Learning

Similar Papers 제목 키워드 기반

Controlled-rearing studies of newborn chicks and deep neural networks

2021-12-12 · NeurIPS Workshop SVRHM 2021 12 · Donsuk Lee, Pranav Gujarathi, Justin N. Wood

Convolutional neural networks (CNNs) can now achieve human-level performance on challenging object recognition tasks. CNNs are also the leading quantitative models in terms of predicting neural and behavioral responses i…

ObjectObject Recognition

A little less conversation, a little more action, please: Investigating the physical common-sense of LLMs in a 3D embodied environment

2024-10-30 · Matteo G. Mecattaf, Ben Slater, Marko Tešić, Jonathan Prunty 외

As general-purpose tools, Large Language Models (LLMs) must often reason about everyday physical environments. In a question-and-answer capacity, understanding the interactions of physical objects may be necessary to giv…

Common Sense ReasoningDeep Reinforcement Learning

Are Vision Transformers More Data Hungry Than Newborn Visual Systems?

2023-12-05 · NeurIPS 2023 11 · Lalit Pandey, Samantha M. W. Wood, Justin N. Wood

Vision transformers (ViTs) are top performing models on many computer vision benchmarks and can accurately predict human behavior on object recognition tasks. However, researchers question the value of using ViTs as mode…

ObjectObject Recognition

A newborn embodied Turing test for view-invariant object recognition

2023-06-08 · Denizhan Pak, Donsuk Lee, Samantha M. W. Wood, Justin N. Wood

Recent progress in artificial intelligence has renewed interest in building machines that learn like animals. Almost all of the work comparing learning across biological and artificial systems comes from studies where an…

Deep Reinforcement LearningObject Recognition

Articulated Animal AI: An Environment for Animal-like Cognition in a Limbed Agent

2024-10-11 · Jeremy Lucas, Isabeau Prémont-Schwarz

This paper presents the Articulated Animal AI Environment for Animal Cognition, an enhanced version of the previous AnimalAI Environment. Key improvements include the addition of agent limbs, enabling more complex behavi…