Thomas Carta
4 papers · 2022–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(3)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
ICML (2)
NAACL (1)
NIPS (1)
Top co-authors
Keywords
reinforcement learning
(2)
large language model
(2)
question answering
(1)
question generation
(1)
online reinforcement learning
(1)
sparse reward
(1)
reward shaping
(1)
intrinsic reward
(1)
contrastive loss
(1)
interactive environment
(1)
prompt overfitting
(1)
agent alignment
(1)
language conditioning
(1)
functional grounding
(1)
contrastive learning
(1)
language-conditioned reinforcement learning
(1)
sample efficiency
(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
NIPS 2022