Maciej Wołczyk
Maciej Wołczyk
Verified email at - Homepage
Cited by
Cited by
Hypernetwork functional image representation
S Klocek, Ł Maziarka, M Wołczyk, J Tabor, J Nowak, M Śmieja
International Conference on Artificial Neural Networks, 496-510, 2019
Urban driver: Learning to drive from real-world demonstrations using policy gradients
O Scheel, L Bergamini, M Wolczyk, B Osiński, P Ondruska
Conference on Robot Learning, 718-728, 2022
Continual world: A robotic benchmark for continual reinforcement learning
M Wołczyk, M Zając, R Pascanu, Ł Kuciński, P Miłoś
Advances in Neural Information Processing Systems 34, 28496-28510, 2021
Safetynet: Safe planning for real-world self-driving vehicles using machine-learned policies
M Vitelli, Y Chang, Y Ye, A Ferreira, M Wołczyk, B Osiński, M Niendorf, ...
2022 International Conference on Robotics and Automation (ICRA), 897-904, 2022
Zero time waste: Recycling predictions in early exit neural networks
M Wołczyk, B Wójcik, K Bałazy, IT Podolak, J Tabor, M Śmieja, T Trzcinski
Advances in Neural Information Processing Systems 34, 2516-2528, 2021
Segma: Semi-supervised Gaussian mixture autoencoder
M Śmieja, M Wołczyk, J Tabor, BC Geiger
IEEE transactions on neural networks and learning systems 32 (9), 3930-3941, 2020
Disentangling transfer in continual reinforcement learning
M Wolczyk, M Zając, R Pascanu, Ł Kuciński, P Miłoś
Advances in Neural Information Processing Systems 35, 6304-6317, 2022
Continual learning with guarantees via weight interval constraints
M Wołczyk, K Piczak, B Wójcik, L Pustelnik, P Morawiecki, J Tabor, ...
International Conference on Machine Learning, 23897-23911, 2022
Plugen: Multi-label conditional generation from pre-trained models
M Wołczyk, M Proszewska, Ł Maziarka, M Zieba, P Wielopolski, ...
Proceedings of the AAAI Conference on Artificial Intelligence 36 (8), 8647-8656, 2022
Biologically-inspired spatial neural networks
M Wołczyk, J Tabor, M Śmieja, S Maszke
arXiv preprint arXiv:1910.02776, 2019
Discovering modular solutions that generalize compositionally
S Schug, S Kobayashi, Y Akram, M Wołczyk, A Proca, J Von Oswald, ...
arXiv preprint arXiv:2312.15001, 2023
Zero time waste in pre-trained early exit neural networks
B Wójcik, M Przewiȩźlikowski, F Szatkowski, M Wołczyk, K Bałazy, ...
Neural Networks 168, 580-601, 2023
On the relationship between disentanglement and multi-task learning
Ł Maziarka, A Nowak, M Wołczyk, A Bedychaj
Joint European Conference on Machine Learning and Knowledge Discovery in …, 2022
Remember more by recalling less: Investigating the role of batch size in continual learning with experience replay (student abstract)
M Wołczyk, A Krutsylo
Proceedings of the AAAI Conference on Artificial Intelligence 35 (18), 15923 …, 2021
Deep learning-based initialization for object packing
M Wołczyk
Schedae Informaticae 27, 2018
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
M Wołczyk, B Cupiał, M Ostaszewski, M Bortkiewicz, M Zając, R Pascanu, ...
arXiv preprint arXiv:2402.02868, 2024
The Effectiveness of World Models for Continual Reinforcement Learning
S Kessler, M Ostaszewski, MP Bortkiewicz, M Żarski, M Wolczyk, ...
Conference on Lifelong Learning Agents, 184-204, 2023
Hebbian Continual Representation Learning
P Morawiecki, A Krutsylo, M Wołczyk, M Śmieja
arXiv preprint arXiv:2207.04874, 2022
Finding the optimal network depth in classification tasks
B Wójcik, M Wołczyk, K Bałazy, J Tabor
Machine Learning and Knowledge Discovery in Databases: European Conference …, 2021
State Soup: In-Context Skill Learning, Retrieval and Mixing
M Pióro, M Wołczyk, R Pascanu, J von Oswald, J Sacramento
arXiv preprint arXiv:2406.08423, 2024
The system can't perform the operation now. Try again later.
Articles 1–20