Matteo Bettini — accepted AI-conference papers

2026

Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments

Romain Froger, Amine Benhalloum, Andrey Rusakov, Dheeraj Mekala, Emilien Garreau, Gerard Moreno-Torres Bertran +18

ICLR 2026oral

We introduce **Gaia2**, a benchmark for evaluating large language model agents in realistic, asynchronous environments. Unlike prior static or synchronous evaluations, Gaia2 introduces scenarios where environments evolve independently of agent actions, requiring agents to operate under temporal cons…

Cited by 0 Source ↗Scholar ↗

2026

When Is Diversity Rewarded in Cooperative Multi-Agent Learning?

Michael Amir, Matteo Bettini, Amanda Prorok

ICLR 2026poster

The success of teams in robotics, nature, and society often depends on the division of labor among diverse specialists; however, a principled explanation for when such diversity surpasses a homogeneous team is still missing. Focusing on multi-agent task allocation problems, we study this question fr…

Cited by 0 Source ↗Scholar ↗

2024

Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning

Matteo Bettini, Ryan Kortvelesy, Amanda Prorok

ICML 2024poster

The study of behavioral diversity in Multi-Agent Reinforcement Learning (MARL) is a nascent yet promising field. In this context, the present work deals with the question of how to control the diversity of a multi-agent system. With no existing approaches to control diversity to a set value, current…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗

2024

TorchRL: A data-driven decision-making library for PyTorch

Albert Bou, Matteo Bettini, Sebastian Dittert, Vikash Kumar, Shagun Sodhani, Xiaomeng Yang +2

ICLR 2024spotlight

PyTorch has ascended as a premier machine learning framework, yet it lacks a native and comprehensive library for decision and control tasks suitable for large development teams dealing with complex real-world data and environments. To address this issue, we propose TorchRL, a generalistic control l…

Cited by 46 Source ↗PDF ↗Scholar ↗

2023

POPGym: Benchmarking Partially Observable Reinforcement Learning

Steven Morad, Ryan Kortvelesy, Matteo Bettini, Stephan Liwicki, Amanda Prorok

ICLR 2023poster

Real world applications of Reinforcement Learning (RL) are often partially observable, thus requiring memory. Despite this, partial observability is still largely ignored by contemporary RL benchmarks and libraries. We introduce Partially Observable Process Gym (POPGym), a two-part library containin…

Cited by 49 Source ↗PDF ↗code ↗Scholar ↗