Thomas Carta

14 papers A* 3Misc 1Journal 8Unranked 1
YearRankTypeTitle / Venue / Authors
2025 J jnl
HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents.
CoRR
Thomas Carta, Clément Romac, Loris Gaven, Pierre-Yves Oudeyer, Olivier Sigaud, Sylvain Lamprier
2025 — —
Language as a cognitive tool for open-ended agents. (Le langage comme outil cognitif pour les agents ouverts).
Thomas Carta
2025 A* conf
MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces.
ICML
Loris Gaven, Thomas Carta, Clément Romac, Cédric Colas, Sylvain Lamprier, Olivier Sigaud, Pierre-Yves Oudeyer
2025 J jnl
MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces.
CoRR
Loris Gaven, Thomas Carta, Clément Romac, Cédric Colas, Sylvain Lamprier, Olivier Sigaud, Pierre-Yves Oudeyer
2025 — conf
Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting.
NAACL (Findings)
Mohamed Salim Aissi, Clément Romac, Thomas Carta, Sylvain Lamprier, Pierre-Yves Oudeyer, Olivier Sigaud, Laure Soulier, Nicolas Thome
2025 J jnl
WorldLLM: Improving LLMs' world modeling using curiosity-driven theory-making.
CoRR
Guillaume Levy, Cédric Colas, Pierre-Yves Oudeyer, Thomas Carta, Clément Romac
2024 Misc conf
Leveraging Visual Handicaps for Text-Based Reinforcement Learning.
ICASSP
Subhajit Chaudhury, Keerthiram Murugesan, Thomas Carta, Kartik Talamadupula, Michiaki Tatsubori
2024 J jnl
Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting.
CoRR
Mohamed Salim Aissi, Clément Romac, Thomas Carta, Sylvain Lamprier, Pierre-Yves Oudeyer, Olivier Sigaud, Laure Soulier, Nicolas Thome
2024 J jnl
SAC-GLAM: Improving Online RL for LLM agents with Soft Actor-Critic and Hindsight Relabeling.
CoRR
Loris Gaven, Clément Romac, Thomas Carta, Sylvain Lamprier, Olivier Sigaud, Pierre-Yves Oudeyer
2023 A* conf
Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning.
ICML
Thomas Carta, Clément Romac, Thomas Wolf, Sylvain Lamprier, Olivier Sigaud, Pierre-Yves Oudeyer
2023 J jnl
Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning.
CoRR
Thomas Carta, Clément Romac, Thomas Wolf, Sylvain Lamprier, Olivier Sigaud, Pierre-Yves Oudeyer
2022 A* conf
EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL.
NeurIPS
Thomas Carta, Pierre-Yves Oudeyer, Olivier Sigaud, Sylvain Lamprier
2022 J jnl
EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL.
CoRR
Thomas Carta, Sylvain Lamprier, Pierre-Yves Oudeyer, Olivier Sigaud
2020 J jnl
VisualHints: A Visual-Lingual Environment for Multimodal Reinforcement Learning.
CoRR
Thomas Carta, Subhajit Chaudhury, Kartik Talamadupula, Michiaki Tatsubori