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

Informazioni relative al progetto

INTERACT

ID dell’accordo di sovvenzione: 101065949

DOI

10.3030/101065949

Data della firma CE 1 Agosto 2022

Data di avvio 1 Ottobre 2022

Data di completamento 31 Agosto 2026

Finanziato da

• Marie Skłodowska-Curie Actions (MSCA)

Costo totale

Nessun dato

Contributo UE

€ 276 681,60

Coordinato da

INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ET AUTOMATIQUE
France

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Documents, reports (1)

Communication, Dissemination & Outreach Plan

The plan describes the planned measures to maximize the impact ofthe project, including the dissemination and exploitation measures that are planned,and the target group(s) addressed. Regarding communication measures and publicengagement strategy, the aim is to inform and reach out to society and show theactivities performed, and the use and the benefits the project will have for citizens.

Data Management Plan (1)

Data Management Plan

The Data Management Plan describes the data management life cyclefor all data sets that will be collected, processed or generated by the action. It is adocument describing what data will be collected, processed or generated andfollowing what methodology and standards, whether and how this data will beshared and/or made open, and how it will be curated and preserved.

Pubblicazioni

Conference proceedings (11)

Policy Learning with a Language Bottleneck

Autori: Megha Srivastava; Cédric Colas; Dorsa Sadigh; Jacob Andreas
Pubblicato in: TMLR, 2026
Editore: TMLR
DOI: 10.48550/ARXIV.2405.04118

When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings

Autori: Jérémy Perez, Grgur Kovač, Corentin Léger, Cédric Colas, Gaia Molinaro, Maxime Derex, Pierre-Yves Oudeyer, Clément Moulin-Frier
Pubblicato in: 2025
Editore: ICLR 2025
DOI: 10.48550/ARXIV.2407.04503

Guiding Pretraining in Reinforcement Learning with Large Language Models

Autori: Du, Yuqing; Watkins, Olivia; Wang, Zihan; Colas, Cédric; Darrell, Trevor; Abbeel, Pieter; Gupta, Abhishek; Andreas, Jacob
Pubblicato in: 2023
Editore: ICML
DOI: 10.48550/ARXIV.2302.06692

ACES: Generating Diverse Programming Puzzles with with Autotelic Generative Models

Autori: Julien Pourcel, Cédric Colas, Gaia Molinaro, Pierre-Yves Oudeyer, Laetitia Teodorescu
Pubblicato in: 2024
Editore: NeurIPS 2024
DOI: 10.48550/ARXIV.2310.10692

Expedition & Expansion: Leveraging Semantic Representations for Goal-Directed Exploration in Continuous Cellular Automata

Autori: Sina Khajehabdollahi, Gautier Hamon, Marko Cvjetko, Pierre-Yves Oudeyer, Clément Moulin-Frier, Cédric Colas
Pubblicato in: 2025
Editore: ALife 2025
DOI: 10.48550/ARXIV.2509.03863

Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI

Autori: Julien Pourcel, Cédric Colas, Pierre-Yves Oudeyer
Pubblicato in: 2025
Editore: ICML 2025
DOI: 10.48550/ARXIV.2507.14172

Language and Experience: A Computational Model of Social Learning in Complex Tasks

Autori: Cédric Colas, Tracey Mills, Ben Prystawski, Michael Henry Tessler, Noah Goodman, Jacob Andreas, Joshua Tenenbaum
Pubblicato in: 2025
Editore: CogSci 2025
DOI: 10.48550/ARXIV.2509.00074

Augmenting Autotelic Agents with Large Language Models

Autori: Cédric Colas, Laetitia Teodorescu, Pierre-Yves Oudeyer, Xingdi Yuan, Marc-Alexandre Côté
Pubblicato in: CoLLAs
Editore: CoLLAs
DOI: 10.48550/ARXIV.2305.12487FOCUSTOLEARNMORE

Latent Learning Progress Drives Autonomous Goal Selection in Human Reinforcement Learning

Autori: Gaia Molinaro, Cédric Colas, Pierre-Yves Oudeyer, Anne Collins
Pubblicato in: 2024
Editore: NeurIPS 2024
DOI: 10.31234/OSF.IO/5DTX3

MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces

Autori: Loris Gaven, Thomas Carta, Clément Romac, Cédric Colas, Sylvain Lamprier, Olivier Sigaud, Pierre-Yves Oudeyer
Pubblicato in: 2025
Editore: ICML 2025
DOI: 10.48550/ARXIV.2502.07709

Goal Inference using Reward-Producing Programs in a Novel Physics Environment

Autori: Davidson, Guy;Todd, Graham;Colas, CŽdric;Chu, Junyi;Togelius, Julian;Tenenbaum, Joshua B.;Gureckis, Todd M;Lake, Brenden
Pubblicato in: 2025
Editore: CogSci 2025