Thomas Carta

4 papers · 2022–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10)

Venues

ICML (2) NAACL (1) NeurIPS (1)

Top co-authors

Olivier Sigaud (4) Pierre-yves Oudeyer (4) Sylvain Lamprier (4) Clément Romac (3) Thomas Wolf (1) Nicolas Thome (1) Loris Gaven (1) Mohamed Salim Aissi (1) Cédric Colas (1) Laure Soulier (1)

Research topics

Artificial Intelligence (3) Reinforcement Learning (3) Core AI (3) Methods (3) Machine Learning (2) Deep Learning (1) Application Areas (1) Learning Types · Deep Learning (1) Learning Types · Machine Learning (1) Optimization & Theory (1)

Keywords

reinforcement learning (2) large language model (2) curriculum learning (1) question answering (1) question generation (1) online reinforcement learning (1) learning progress (1) autotelic agent (1) sparse reward (1) reward shaping (1) intrinsic reward (1) contrastive loss (1) interactive environment (1) goal prioritization (1) prompt overfitting (1) agent alignment (1) language conditioning (1) functional grounding (1) online rl (1) language-conditioned reinforcement learning (1)

Papers

MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces ICML 2025 Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting NAACL 2025 Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning ICML 2023 EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL NeurIPS 2022