- PhD Student
Research
• Graph Neural Networks
• Multi-Agent Reinforcement Learning
Teaching
Demonstrator for Mobile Robot Systems
Supervisor for Foundations of Computer Science
Publications
Ryan Kortvelesy, Steven Morad, and Amanda Prorok. Generalised f-Mean Aggregation for Graph Neural Networks. Advances in Neural Information Processing Systems (NeurIPS), 2023.
Steven Morad, Ryan Kortvelesy, Stephan Liwicki, Amanda Prorok. Reinforcement Learning with Fast and Forgetful Memory. Advances in Neural Information Processing Systems (NeurIPS), 2023.
Ryan Kortvelesy, Steven Morad, and Amanda Prorok. Permutation-Invariant Set Autoencoders with Fixed-Size Embeddings for Multi-Agent Learning. Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2023.
Steven Morad, Ryan Kortvelesy, Matteo Bettini, Stephan Liwicki, and Amanda Prorok. POPGym: Benchmarking Partially Observable Reinforcement Learning. International Conference on Learning Representations (ICLR), 2023.
Ryan Kortvelesy and Amanda Prorok. ModGNN: Expert Policy Approximation in Multi-Agent Systems with a Modular Graph Neural Network Architecture. IEEE International Conference on Robotics and Automation (ICRA), 2021.
Ryan Kortvelesy. Fixed Integral Neural Networks. Arxiv, 2023.
Matteo Bettini, Ryan Kortvelesy, Jan Blumenkamp, and Amanda Prorok. VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning. Proceedings of the 16th International Symposium on Distributed Autonomous Robotic Systems (DARS), 2022.
Ryan Kortvelesy and Amanda Prorok. QGNN: Value Function Factorisation with Graph Neural Networks. Arxiv, 2022.
Steven Morad, Stephan Liwicki, Ryan Kortvelesy, Roberto Mecca, and Amanda Prorok. Modeling Partially Observable Systems using Graph-Based Memory and Topological Priors. Learning for Dynamics and Control Conference (L4DC), 2022.
Jennifer Gielis, Ajay Shankar, Ryan Kortvelesy, and Amanda Prorok. Modeling Aggregate Downwash Forces for Dense Multirotor Flight. International Symposium on Experimental Robotics (ISER), 2023.
Amanda Prorok, Jan Blumenkamp, Qingbiao Li, Ryan Kortvelesy, Zhe Liu, and Ethan Stump. The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions from Offline-Optimal Experts. Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2022.
