7 citations · 20 across the 11 of their papers we have counts for
11 papers
PRISM: Perception Reasoning Interleaved for Sequential Decision Making
Mohamed Salim Aissi, Clemence Grislain, Clement Romac +4
Scaling LLM-based embodied agents from text-only environments to complex multimodal settings remains a major challenge. Recent work identifies a perception-reasoning-decision gap i…
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…
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…
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…
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…
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…
Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent
Quentin Gallouédec, Edward Beeching, Clément Romac +1
The search for a general model that can operate seamlessly across multiple domains remains a key goal in machine learning research. The prevailing methodology in Reinforcement Lear…
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…
TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL
Clément Romac, Rémy Portelas, Katja Hofmann +1
Training autonomous agents able to generalize to multiple tasks is a key target of Deep Reinforcement Learning (DRL) research. In parallel to improving DRL algorithms themselves, A…
Meta Automatic Curriculum Learning
Rémy Portelas, Clément Romac, Katja Hofmann +1
A major challenge in the Deep RL (DRL) community is to train agents able to generalize their control policy over situations never seen in training. Training on diverse tasks has be…
Deep Recurrent Q-Learning vs Deep Q-Learning on a simple Partially Observable Markov Decision Process with Minecraft
Clément Romac, Vincent Béraud
Deep Q-Learning has been successfully applied to a wide variety of tasks in the past several years. However, the architecture of the vanilla Deep Q-Network is not suited to deal wi…