Peter Vrancx
Peter Vrancx
Principal Researcher at IMEC
Verified email at
Cited by
Cited by
Game theory and multi-agent reinforcement learning
A Nowť, P Vrancx, YM De Hauwere
Reinforcement Learning: State-of-the-Art, 441-470, 2012
Forecasting day-ahead electricity prices in Europe: The importance of considering market integration
J Lago, F De Ridder, P Vrancx, B De Schutter
Applied energy 211, 890-903, 2018
Convolutional neural networks for automatic state-time feature extraction in reinforcement learning applied to residential load control
BJ Claessens, P Vrancx, F Ruelens
IEEE Transactions on Smart Grid 9 (4), 3259-3269, 2016
Expressing arbitrary reward functions as potential-based advice
A Harutyunyan, S Devlin, P Vrancx, A Nowť
Proceedings of the AAAI conference on artificial intelligence 29 (1), 2015
Decentralized learning in markov games
P Vrancx, K Verbeeck, A Nowť
IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 38†…, 2008
Multi-objectivization of reinforcement learning problems by reward shaping
T Brys, A Harutyunyan, P Vrancx, ME Taylor, D Kudenko, A Nowť
2014 international joint conference on neural networks (IJCNN), 2315-2322, 2014
Learning multi-agent state space representations
YM De Hauwere, P Vrancx, A Nowť
Proceedings of the 9th International Conference on Autonomous Agents and†…, 2010
Soft q-learning with mutual-information regularization
J Grau-Moya, F Leibfried, P Vrancx
International Conference on Learning Representations, 2018
DIANA: An end-to-end energy-efficient digital and ANAlog hybrid neural network SoC
K Ueyoshi, IA Papistas, P Houshmand, GM Sarda, V Jain, M Shi, Q Zheng, ...
2022 IEEE International Solid-State Circuits Conference (ISSCC) 65, 1-3, 2022
Multi-objectivization and ensembles of shapings in reinforcement learning
T Brys, A Harutyunyan, P Vrancx, A Nowť, ME Taylor
Neurocomputing 263, 48-59, 2017
Direct load control of thermostatically controlled loads based on sparse observations using deep reinforcement learning
F Ruelens, BJ Claessens, P Vrancx, F Spiessens, G Deconinck
CSEE Journal of Power and Energy Systems 5 (4), 423-432, 2019
Switching dynamics of multi-agent learning.
P Vrancx, K Tuyls, RL Westra, A Nowť
AAMAS (1) 2008, 307-313, 2008
Multi-type ant colony: The edge disjoint paths problem
A Nowť, K Verbeeck, P Vrancx
Ant Colony Optimization and Swarm Intelligence: 4th International Workshop†…, 2004
A model based on ant colony system and rough set theory to feature selection
R Bello, A Nowe, Y Caballero, Y Gůmez, P Vrancx
Proceedings of the 7th annual conference on genetic and evolutionary†…, 2005
Improving wet clutch engagement with reinforcement learning
K Van Vaerenbergh, A RodrŪguez, M Gagliolo, P Vrancx, A Nowť, J Stoev, ...
The 2012 International Joint Conference on Neural Networks (IJCNN), 1-8, 2012
Machine learning system
A Tukiainen, D Kim, T Nicholson, M Tomczak, JEMDEC FLORES, ...
US Patent App. 16/753,580, 2020
Predicting seat-off and detecting start-of-assistance events for assisting sit-to-stand with an exoskeleton
K Tanghe, A Harutyunyan, E AertbeliŽn, F De Groote, J De Schutter, ...
IEEE Robotics and Automation Letters 1 (2), 792-799, 2016
Transfer learning for multi-agent coordination
P Vrancx, YM De Hauwere, A Nowť
International Conference on Agents and Artificial Intelligence 2, 263-272, 2011
Learning with options that terminate off-policy
A Harutyunyan, P Vrancx, PL Bacon, D Precup, A Nowe
Proceedings of the AAAI Conference on Artificial Intelligence 32 (1), 2018
Reinforcement learning in POMDPs with memoryless options and option-observation initiation sets
D Steckelmacher, D Roijers, A Harutyunyan, P Vrancx, H Plisnier, A Nowť
Proceedings of the AAAI conference on artificial intelligence 32 (1), 2018
The system can't perform the operation now. Try again later.
Articles 1–20