7 papers
JEF-Hinter: Leveraging Offline Knowledge for Improving Web Agents Adaptation
Hadi Nekoei, Aman Jaiswal, Patrice Bechard +7
Large language model (LLM) agents perform well in sequential decision-making tasks, but improving them on unfamiliar domains often requires costly online interactions or fine-tunin…
How to Train Your LLM Web Agent: A Statistical Diagnosis
Dheeraj Vattikonda, Santhoshi Ravichandran, Emiliano Penaloza +13
LLM-based web agents have recently made significant progress, but much of it has occurred in closed-source systems, widening the gap with open-source alternatives. Progress has bee…
Shielded Controller Units for RL with Operational Constraints Applied to Remote Microgrids
Hadi Nekoei, Alexandre Blondin Massé, Rachid Hassani +2
Reinforcement learning (RL) is a powerful framework for optimizing decision-making in complex systems under uncertainty, an essential challenge in real-world settings, particularly…
Balancing Profit and Fairness in Risk-Based Pricing Markets
Jesse Thibodeau, Hadi Nekoei, Afaf Taïk +2
Dynamic, risk-based pricing can systematically exclude vulnerable consumer groups from essential resources such as health insurance and consumer credit. We show that a regulator ca…
A Generalist Hanabi Agent
Arjun V Sudhakar, Hadi Nekoei, Mathieu Reymond +3
Traditional multi-agent reinforcement learning (MARL) systems can develop cooperative strategies through repeated interactions. However, these systems are unable to perform well on…
Generative Active Learning for the Search of Small-molecule Protein Binders
Maksym Korablyov, Cheng-Hao Liu, Moksh Jain +31
Despite substantial progress in machine learning for scientific discovery in recent years, truly de novo design of small molecules which exhibit a property of interest remains a si…