Publications
Tutorials & Seminars
I am really proud to have co-organised the Evolutionary Reinforcement Learning Tutorial at GECCO in 2024 and 2025, together with Bryan Lim, Paul Templier, and Antoine Cully!
During my PhD, I was also part of the organising committee for the Imperial College Autonomous Reasoning and Learning (ICARL) seminars.
2026
Amir*, M., Flageat*, M., & Prorok, A. (2026). Remotely Detectable Robot Policy Watermarking. International Conference on Learning Representations (ICLR 2026).
Chang, B., Amir, M., Flageat, M., & Prorok, A. (2026). Remotely Detectable Keyed Communication through Motion. arXiv preprint.
Bächi, H., Flageat, M., Sebastián, E., & Prorok, A. (2026). Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning. arXiv preprint.
2025
Allard*, M., Flageat*, M., Lim, B., & Cully, A. (2025). Getting Robots Back on Track by Reconstituting Control in Unexpected Situations with Online Learning. Nature Communications.
Flageat, M., Huber, J., Helenon, F., Doncieux, S., & Cully, A. Extract-QD Framework: A Generic Approach for Quality-Diversity in Noisy, Stochastic or Uncertain Domains. Proceedings of the Genetic and Evolutionary Computation Conference.
- Paper
- GECCO 2025 Best Paper Award
Flageat, M., Janmohamed, H., Lim, B., & Cully, A. (2024). Exploring the Performance-Reproducibility Trade-off in Quality-Diversity. IEEE Transactions on Evolutionary Computation.
Faldor, M., Chalumeau, F., Flageat, M., & Cully, A. (2024). Synergizing Quality-Diversity with Descriptor-Conditioned Reinforcement Learning. ACM Transactions on Evolutionary Learning and Optimization.
2024
Chalumeau, F. and Lim, B. and Boige, R. and Allard, M. and Grillotti, L. and Flageat, M. and Macé, V. and Richard, G. and Flajolet, A. and Pierrot, T. and Cully, A. (2024). QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration. Journal of Machine Learning Research 25, 1-16.
Flageat*, M., Lim*, B., & Cully, A. (2024). Beyond Expected Return: Accounting for Policy Reproducibility when Evaluating Reinforcement Learning Algorithm. The 38th Annual AAAI Conference on Artificial Intelligence (AAAI 2024).
Flageat*, M., Lim*, B., & Cully, A. (2024). Enhancing Quality and Diversity using MAP-Elites with Multiple Parallel Evolution Strategies. Proceedings of the Genetic and Evolutionary Computation Conference.
Lim, B., Flageat, M., & Cully, A. (2024). Large Language Models as In-context AI Generators for Quality-Diversity. ALIFE 2024: The 2024 Conference on Artificial Life.
2023
Flageat, M., & Cully, A. (2023). Uncertain Quality-Diversity: Evaluation methodology and new methods for Quality-Diversity in Uncertain Domains. IEEE Transactions on Evolutionary Computation.
Flageat, M., Chalumeau, F., & Cully, A. (2023). Empirical analysis of PGA-MAP-Elites for Neuroevolution in Uncertain Domains. ACM Transactions on Evolutionary Learning, 3(1), 1–32.
- Paper
- Editor-in-Chief’s Featured Articles 2023
Lim*, B., Flageat*, M., & Cully, A. (2023). Understanding the Synergies between Quality-Diversity and Deep Reinforcement Learning. Proceedings of the Genetic and Evolutionary Computation Conference.
Grillotti*, L., Flageat*, M., Lim, B., & Cully, A. (2023). Don’t Bet on Luck Alone: Enhancing Behavioral Reproducibility of Quality-Diversity Solutions in Uncertain Domains. Proceedings of the Genetic and Evolutionary Computation Conference.
Faldor, M., Chalumeau, F., Flageat, M., & Cully, A. (2023). MAP-Elites with Descriptor-Conditioned Gradients and Archive Distillation into a Single Policy. Proceedings of the Genetic and Evolutionary Computation Conference.
- Paper
- GECCO 2023 Best Paper Award
Lim*, B., Flageat*, M., & Cully, A. (2023). Efficient Exploration using Model-Based Quality-Diversity with Gradients. ALIFE 2023: The 2023 Conference on Artificial Life.
Flageat, M., Grillotti, L., & Cully, A. (2023). Benchmark Tasks for Quality-Diversity Applied to Uncertain Domains. Quality-Diversity Benchmark Workshop, Proceedings of Companion Conference on Genetic and Evolutionary Computation Conference.
Ingvarsson, G., Samvelyan, M., Lim, B., Flageat, M., Cully, A., Rocktäschel, T., (2023). Mix-ME: Quality-Diversity for Multi-Agent Learning. Agent Learning in Open-Endedness (ALOE) Workshop, NeurIPS 2023.
2022
Lim*, B., Flageat*, M., & Cully, A. (2022). Efficient Exploration using Model-Based Quality-Diversity with Gradients. Deep Reinforcement Learning Workshop NeurIPS 2022.
Flageat*, M., Lim*, B., Grillotti, L., Allard, M., Smith, S. C., & Cully, A. (2022). Benchmarking Quality-Diversity Algorithms on Neuroevolution for Reinforcement Learning. QD Benchmark Workshop - Genetic and Evolutionary Computation Conference.
2020
Flageat, M., & Cully, A. (2020). Fast and stable MAP-Elites in noisy domains using deep grids. ALIFE 2020: The 2020 Conference on Artificial Life, 273–282.
Flageat, M., Arulkumaran, K., & Bharath, A. A. (2020). Incorporating Human Priors into Deep Reinforcement Learning for Robotic Control. ESANN, 229–234.
Note
* denotes equal contribution.