I am a researcher and computer scientist with interests in the investigation and development of general purpose intelligent systems, and their application in scientific (e.g., biology and health) and real-world problems. To this end, my research interests cut across several areas in machine learning which include: reinforcement learning, meta-learning, lifelong learning, continual learning, Hebbian learning, neuromodulation, and neuroevolution. I currently work on the research and development of intelligent systems for air traffic control (aviation) problems exploiting reinforcement learning and imitation learning as the underpinning techniques. Previously, I worked on two DARPA-funded lifelong learning research programmes: lifelong learning machines (L2M) and shared-experience lifelong learning (ShELL).

Preprint(s)

• The configurable tree graph (CT-graph): measurable problems in partially observable and distal reward environments for lifelong reinforcement learning
  A. Soltoggio, E. Ben, C. Peridis, P. Ladosz, J. Dick, P. K. Pilly, S. Kolouri.

Publications

• Online Action-Stacking Improves Reinforcement Learning Performance for Air Traffic Control
  B. J. Carvell, G. De Ath, E. Ben, R. Everson. In AIAA SCITECH 2026 Forum (p. 2746), 2026.

• Towards Transparent AI Agents for Air Traffic Control
  E. Mohamed, B. J. Carvell, R. Procter, E. Ben, G. De Ath, R. Everson. In AIAA SCITECH 2026 Forum (p. 2869), 2026.

• Policy Search, Retrieval, and Composition via Task Similarity in Collaborative Agentic Systems
  S. Nath, C. Peridis, E. Ben, X. Liu, S. Kolouri, P. Kinnell, Z. Li, C. Liu, S. Dora, A. Soltoggio. AAAI Conference on Artificial Intelligence, 2026.

• Statistical Context Detection for Deep Lifelong Reinforcement Learning
  J. Dick, S. Nath, C. Peridis, E. Ben, S. Kolouri, A. Soltoggio. Conference on Lifelong Learning Agents (CoLLAs), 2024.

• A Collective AI via Lifelong Learning and Sharing at the Edge
  A. Soltoggio, E. Ben, V. Braverman, E. Eaton, B. Epstein, Y. Ge, L. Halperin, J. How, L. Itti, M. A. Jacobs, et al. Nature Machine Intelligence, vol. 6, no. 3, pp. 251–264, 2024.

• Sharing Lifelong Reinforcement Learning Knowledge via Modulating Masks
  S. Nath, C. Peridis, E. Ben, X. Liu, S. Dora, C. Liu, S. Kolouri, A. Soltoggio. Conference on Lifelong Learning Agents (CoLLAs), 2023.

• Lifelong Reinforcement Learning with Modulating Masks
  E. Ben, S. Nath, P. K. Pilly, S. Kolouri, A. Soltoggio. Transactions on Machine Learning Research (TMLR), 2023.

• A domain-agnostic approach for characterization of lifelong learning systems
  M. M. Baker, A. New, M. Aguilar-Simon, Z. Al-Halah, S. M. R. Arnold, E. Ben, A. P. Brna, E. Brooks, R. C. Brown, Z. Daniels, A. Daram, F. Delattre, R. Dellana, E. Eaton, H. Fu, K. Grauman, J. Hostetler, S. Iqbal, C. Kent, N. Ketz, S. Kolouri, G. Konidaris, D. Kudithipudi, E. Learned-Miller, S. Lee, M. L. Littman, S. Madireddy, J. A. Mendez, E. Q. Nguyen, C. D. Piatko, P. K. Pilly, A. Raghavan, A. Rahman, S. K. Ramakrishnan, N. Ratzlaff, A. Soltoggio, P. Stone, I. Sur, Z. Tang, S. Tiwari, K. Vedder, F. Wang, Z. Xu, A. Yanguas-Gil, H. Yedidsion, S. Yu, G. K. Vallabha. Journal of Neural Networks, 2023.

• Context Meta-Reinforcement Learning via Neuromodulation
  E. Ben, J. Dick, N.A. Ketz, P.K. Pilly, and A. Soltoggio. Journal of Neural Networks, 2022.

• Deep reinforcement learning with modulated hebbian plus q-network architecture
  P. Ladosz, E. Ben, J. Dick, N. Ketz, S. Kolouri, J. L. Krichmar, P. K. Pilly, and A. Soltoggio. IEEE Transactions on Neural Networks and Learning Systems, 2021.

• Evolving inborn knowledge for fast adaptation in dynamic pomdp problems
  E. Ben, P. Ladosz, J. Dick, W.-H. Chen, P. Pilly, and A. Soltoggio. In Proceedings of the Genetic and Evolutionary Computation Conference, 2020.

• Detecting changes and avoiding catastrophic forgetting in dynamic partially observable environments
  J. Dick, P. Ladosz, E. Ben, H. Shimadzu, P. Kinnell, P. K. Pilly, and A. Soltoggio. Frontiers in Neurorobotics, vol. 14, p. 103, 2020.