Carta, Thomas

6 publications

ICML 2025 MAGELLAN: Metacognitive Predictions of Learning Progress Guide Autotelic LLM Agents in Large Goal Spaces Loris Gaven, Thomas Carta, Clément Romac, Cédric Colas, Sylvain Lamprier, Olivier Sigaud, Pierre-Yves Oudeyer

NeurIPSW 2024 Autotelic LLM-Based Exploration for Goal-Conditioned RL Guillaume Pourcel, Thomas Carta, Grgur Kovač, Pierre-Yves Oudeyer

NeurIPSW 2024 SAC-GLAM: Improving Online RL for LLM Agents with Soft Actor-Critic and Hindsight Relabeling Loris Gaven, Thomas Carta, Clément Romac, Olivier Sigaud, Sylvain Lamprier, Pierre-Yves Oudeyer

NeurIPSW 2023 Codeplay: Autotelic Learning Through Collaborative Self-Play in Programming Environments Laetitia Teodorescu, Cédric Colas, Matthew Bowers, Thomas Carta, Pierre-Yves Oudeyer

ICML 2023 Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning Thomas Carta, Clément Romac, Thomas Wolf, Sylvain Lamprier, Olivier Sigaud, Pierre-Yves Oudeyer

NeurIPS 2022 EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-Guided RL Thomas Carta, Pierre-Yves Oudeyer, Olivier Sigaud, Sylvain Lamprier