HEИндивидуална стипендия2022–2026

INTERACT · Help Me Grow: Artificial Cognitive Development via Human-Agent Interactions Supported by New Interactive, Intrinsically Motivated Program Synthesis Methods.

„Хоризонт Европа“ — Действия „Мария Склодовска-Кюри“

Период: 2022-10-01 → 2026-08-31
Финансиране от ЕС: 276 682 €
Участници: 2
Схема: HORIZON-TMA-MSCA-PF-GF

Линиите свързват координатора с партньорите.

Накратко на български

Изкуственият интелект се изучава да избира цели самостоятелно и да се учи чрез общуване с хора, подобно на дете. Това помага за създаването на системи, които се адаптират по-гъвкаво и обясняват действията си по разбираем начин.

Този кратък обзор е генериран от изкуствен интелект

Кратко обяснение, генерирано от езиков модел по текста на CORDIS. Оригиналът е по-долу.

Резултати накратко

Help Me Grow: Artificial Cognitive Development via Human-Agent Interactions Supported by New Interactive, Intrinsically Motivated Program Synthesis Methods.

Artificial intelligence systems are usually designed for fixed tasks and predefined objectives. They often struggle to decide what to learn next, adapt their goals over time, or explain their behavior in ways people can understand. Humans, by contrast, learn in an open-ended way: they choose goals based on how much they expect to learn, adjust these goals through experience and social interaction, and use language to share advice, rules, and strategies. This project studied how to design learning systems that can operate in a similar open-ended but human-aligned manner. The project pursued three main objectives. The first was to understand how humans select their own learning goals and what internal signals guide this process. The second was to study how language and social interaction can guide learning and decision making. The third was to design and evaluate artificial agents that can autonomously select goals and learning curricula in large and evolving task spaces, while remaining interpretable and responsive to human guidance.

Текст от CORDIS, на английски · Данни: CORDIS, © Европейски съюз

Цел на проекта

Building machines that interact with their world, discover interesting interactions and learn open-ended repertoires of skills is a long-standing goal in AI. This project aims at tackling the limits of current AI systems by building on three families of methods: Bayesian program induction, intrinsically motivated learning and human-machine linguistic interactions. It targets three objectives: 1) building autonomous agents that learn to generate programs to solve problems with occasional human guidance; 2) studying linguistic interactions between humans and machines via web-based experiments (e.g. properties of human guidance, its impact on learning, human subjective evaluations); and 3) scaling the approach to the generation of constructions in Minecraft, guided by real players. The researcher will collaborate with scientific pioneers and experts in the key fields and methods supporting the project. This includes supervisors Joshua Tenenbaum (program synthesis, MIT) and Pierre-Yves Oudeyer (autonomous learning, Inria); diverse collaborators, and an advisory board composed of an entrepreneur and leading scientists in developmental psychology and human-robot interactions. The 3rd objective will be pursued via a secondment with Thomas Wolf (CSO) at HuggingFace, a world-leading company in the open source development of natural language processing methods and their transfer to the industry. By enabling users to participate in the training of artificial agents, the project aims to open research avenues for more interpretable, performant and adaptive AI systems. This will result in scientific (e.g. interactive program synthesis approaches), societal (e.g. democratized AI training) and economic impacts (e.g. adaptive AI assistants). The dissemination, communication and exploitation plans support these objectives by targeting scientific (AI, cognitive science), industrial (video games, smart homes) and larger communities (gamers, software engineers, large public).

Оригинален текст от CORDIS (на английски).

Участници

INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ET AUTOMATIQUE · Le Chesnay CedexКоординаторФранция
MASSACHUSETTS INSTITUTE OF TECHNOLOGY · CambridgeСъединени щати