Florian Felten

Florian Felten

I'm working on building something new @ Autom8.

Publications

You can also find my articles on my Google Scholar profile.

MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning

Published in DMLR , 2026

The first unified API for multi-objective multi-agent RL.

Recommended citation: Florian Felten, Umut Ucak, Hicham Azmani, Gao Peng, Willem Röpke, Hendrik Baier, Patrick Mannion, Diederik M. Roijers, Jordan K. Terry, El Ghazali Talbi, Grégoire Danoy, Ann Nowé, Roxana Rădulescu ‘MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning’, in Journal of Data-centric Machine Learning Research, 2026.
Download Paper

EngiBench: A Framework for Data-Driven Engineering Design Research

Published in NeurIPS 2025, 2025

The first unified API for engineering design optimization and ML research.

Recommended citation: Florian Felten, Gabriel Apaza, Gerhard Bräunlich, Cashen Diniz, XULIANG DONG, Arthur Drake, Milad Habibi, Nathaniel James Hoffman, Matthew Keeler, Soheyl Massoudi, Francis VanGessel, Mark Fuge ‘EngiBench: A Framework for Data-Driven Engineering Design Research’, in NeurIPS 2025.
Download Paper

Multi-Objective Reinforcement Learning

Published in Université du Luxembourg [FSTM], 2024

My Thesis on Multi-Objective Reinforcement Learning

Recommended citation: Florian Felten, ‘Multi-Objective Reinforcement Learning’, in Unilu - Université du Luxembourg [FSTM], Luxembourg.
Download Paper

A Toolkit for Reliable Benchmarking and Research in Multi-Objective Reinforcement Learning

Published in Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2023

MO-Gymnasium + MORL-baselines + Public datasets of training results.

Recommended citation: Florian Felten, Lucas Nunes Alegre, Ann Nowe, Ana L. C. Bazzan, El Ghazali Talbi, Grégoire Danoy, and Bruno Castro da Silva, ‘A Toolkit for Reliable Benchmarking and Research in Multi-Objective Reinforcement Learning’, in Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS 2023).
Download Paper

MO-Gym: A Library of Multi-Objective Reinforcement Learning Environments

Published in BNAIC/BeNeLearn 22, 2022

Open source library for Multi-Objective RL.

Recommended citation: L. N. Alegre, F. Felten, E.-G. Talbi, G. Danoy, A. Nowé, and A. L. C. Bazzan, “MO-Gym: A Library of Multi-Objective Reinforcement Learning Environments,” Proceedings of the 34th Benelux Conference on Artificial Intelligence BNAIC/Benelearn 2022
Download Paper

MORL/D: Multi-Objective Reinforcement Learning based on Decomposition

Published in International Conference in Optimization and Learning (OLA2022), 2022

Applying decomposition techniques from MOO to MORL.

Recommended citation: F. Felten, E.-G. Talbi, and G. Danoy, (2022). MORL/D: Multi-Objective Reinforcement Learning based on Decomposition. In Proceedings of International Conference on Optimization and Learning (OLA2022)
Download Paper

Metaheuristics-based Exploration Strategies for Multi-Objective Reinforcement Learning

Published in Proceedings of the 14th International Conference on Agents and Artificial Intelligence, 2022

Nominated for best student paper award.

Recommended citation: Felten, F., Danoy, G., Talbi, E. and Bouvry, P. (2022). Metaheuristics-based Exploration Strategies for Multi-Objective Reinforcement Learning. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-547-0; ISSN 2184-433X, pages 662-673. DOI: 10.5220/0010989100003116.
Download Paper