6 papers
Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning
Thomas Carta, Clément Romac, Thomas Wolf +3
Recent works successfully leveraged Large Language Models' (LLM) abilities to capture abstract knowledge about world's physics to solve decision-making problems. Yet, the alignment…
WorldLLM: Improving LLMs' world modeling using curiosity-driven theory-making
Guillaume Levy, Cedric Colas, Pierre-Yves Oudeyer +2
Large Language Models (LLMs) possess general world knowledge but often struggle to generate precise predictions in structured, domain-specific contexts such as simulations. These l…
SAC-GLAM: Improving Online RL for LLM agents with Soft Actor-Critic and Hindsight Relabeling
Loris Gaven, Clement Romac, Thomas Carta +3
The past years have seen Large Language Models (LLMs) strive not only as generative models but also as agents solving textual sequential decision-making tasks. When facing complex…
Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting
Mohamed Salim Aissi, Clement Romac, Thomas Carta +5
Reinforcement learning (RL) is a promising approach for aligning large language models (LLMs) knowledge with sequential decision-making tasks. However, few studies have thoroughly…
HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents
Thomas Carta, Clément Romac, Loris Gaven +3
We study goal-conditioned reinforcement learning in partially observable environments with sparse rewards and large, structured goal spaces. In such settings, complex goals often r…
MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces
Loris Gaven, Thomas Carta, Clément Romac +4
Open-ended learning agents must efficiently prioritize goals in vast possibility spaces, focusing on those that maximize learning progress (LP). When such autotelic exploration is…