Follow
Ryan Kortvelesy
Ryan Kortvelesy
Verified email at cam.ac.uk
Title
Cited by
Cited by
Year
ModGNN: Expert policy approximation in multi-agent systems with a modular graph neural network architecture
R Kortvelesy, A Prorok
2021 IEEE International Conference on Robotics and Automation (ICRA), 9161-9167, 2021
202021
POPGym: Benchmarking Partially Observable Reinforcement Learning
S Morad, R Kortvelesy, M Bettini, S Liwicki, A Prorok
arXiv preprint arXiv:2303.01859, 2023
172023
VMAS: a vectorized multi-agent simulator for collective robot learning
M Bettini, R Kortvelesy, J Blumenkamp, A Prorok
arXiv preprint arXiv:2207.03530, 2022
112022
The holy grail of multi-robot planning: Learning to generate online-scalable solutions from offline-optimal experts
A Prorok, J Blumenkamp, Q Li, R Kortvelesy, Z Liu, E Stump
arXiv preprint arXiv:2107.12254, 2021
82021
QGNN: Value Function Factorisation with Graph Neural Networks
R Kortvelesy, A Prorok
arXiv preprint arXiv:2205.13005, 2022
72022
sUAS for deployment and recovery of an environmental sensor probe
L Vacek, E Atter, P Rizo, B Nam, R Kortvelesy, D Kaufman, J Das, ...
2017 International Conference on Unmanned Aircraft Systems (ICUAS), 1022-1029, 2017
62017
Reinforcement Learning with Fast and Forgetful Memory
S Morad, R Kortvelesy, S Liwicki, A Prorok
Advances in Neural Information Processing Systems 36, 2024
12024
Fixed Integral Neural Networks
R Kortvelesy
arXiv preprint arXiv:2307.14439, 2023
12023
Graph Convolutional Memory using Topological Priors
SD Morad, S Liwicki, R Kortvelesy, R Mecca, A Prorok
arXiv preprint arXiv:2106.14117, 2021
12021
Revisiting Recurrent Reinforcement Learning with Memory Monoids
S Morad, C Lu, R Kortvelesy, S Liwicki, J Foerster, A Prorok
arXiv preprint arXiv:2402.09900, 2024
2024
Generalised f-Mean Aggregation for Graph Neural Networks
R Kortvelesy, S Morad, A Prorok
Advances in Neural Information Processing Systems 36, 2024
2024
Modeling Aggregate Downwash Forces for Dense Multirotor Flight
J Gielis, A Shankar, R Kortvelesy, A Prorok
arXiv preprint arXiv:2312.03488, 2023
2023
Permutation-Invariant Set Autoencoders with Fixed-Size Embeddings for Multi-Agent Learning
R Kortvelesy, S Morad, A Prorok
arXiv preprint arXiv:2302.12826, 2023
2023
Modeling Partially Observable Systems using Graph-Based Memory and Topological Priors
S Morad, S Liwicki, R Kortvelesy, R Mecca, A Prorok
Learning for Dynamics and Control Conference, 59-73, 2022
2022
The system can't perform the operation now. Try again later.
Articles 1–14