Maciej Wolczyk

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 34

Top Topics

Reinforcement Learning

Gaussian Mixture

Top Venues

Publications

Adam Pardyl, Michal Wronka, Maciej Wolczyk, Kamil Adamczewski, Tomasz Trzcinski, Bartosz Zielinski
AdaGlimpse: Active Visual Exploration with Arbitrary Glimpse Position and Scale. CoRR (2024)
Maciej Pióro, Maciej Wolczyk, Razvan Pascanu, Johannes von Oswald, João Sacramento
State Soup: In-Context Skill Learning, Retrieval and Mixing. CoRR (2024)
Magdalena Proszewska, Maciej Wolczyk, Maciej Zieba, Patryk Wielopolski, Lukasz Maziarka, Marek Smieja
Multi-Label Conditional Generation From Pre-Trained Models. IEEE Trans. Pattern Anal. Mach. Intell. 46 (9) (2024)
Simon Schug, Seijin Kobayashi, Yassir Akram, Maciej Wolczyk, Alexandra Proca, Johannes von Oswald, Razvan Pascanu, João Sacramento, Angelika Steger
Discovering modular solutions that generalize compositionally. ICLR (2024)
Maciej Wolczyk, Bartlomiej Cupial, Mateusz Ostaszewski, Michal Bortkiewicz, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem. CoRR (2024)
Bartosz Wójcik, Marcin Przewiezlikowski, Filip Szatkowski, Maciej Wolczyk, Klaudia Balazy, Bartlomiej Krzepkowski, Igor T. Podolak, Jacek Tabor, Marek Smieja, Tomasz Trzcinski
Zero time waste in pre-trained early exit neural networks. Neural Networks 168 (2023)
Simon Schug, Seijin Kobayashi, Yassir Akram, Maciej Wolczyk, Alexandra Proca, Johannes von Oswald, Razvan Pascanu, João Sacramento, Angelika Steger
Discovering modular solutions that generalize compositionally. CoRR (2023)
Pawel Morawiecki, Andrii Krutsylo, Maciej Wolczyk, Marek Smieja
Hebbian Continual Representation Learning. HICSS (2023)
Samuel Kessler, Mateusz Ostaszewski, Michal Pawel Bortkiewicz, Mateusz Zarski, Maciej Wolczyk, Jack Parker-Holder, Stephen J. Roberts, Piotr Milos
The Effectiveness of World Models for Continual Reinforcement Learning. CoLLAs (2023)
Matt Vitelli, Yan Chang, Yawei Ye, Ana Ferreira, Maciej Wolczyk, Blazej Osinski, Moritz Niendorf, Hugo Grimmett, Qiangui Huang, Ashesh Jain, Peter Ondruska
SafetyNet: Safe Planning for Real-World Self-Driving Vehicles Using Machine-Learned Policies. ICRA (2022)
Maciej Wolczyk, Magdalena Proszewska, Lukasz Maziarka, Maciej Zieba, Patryk Wielopolski, Rafal Kurczab, Marek Smieja
PluGeN: Multi-Label Conditional Generation from Pre-trained Models. AAAI (2022)
Maciej Wolczyk, Karol J. Piczak, Bartosz Wójcik, Lukasz Pustelnik, Pawel Morawiecki, Jacek Tabor, Tomasz Trzcinski, Przemyslaw Spurek
Continual Learning with Guarantees via Weight Interval Constraints. ICML (2022)
Maciej Wolczyk, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos
Disentangling Transfer in Continual Reinforcement Learning. CoRR (2022)
Lukasz Maziarka, Aleksandra Nowak, Maciej Wolczyk, Andrzej Bedychaj
On the Relationship Between Disentanglement and Multi-task Learning. ECML/PKDD (1) (2022)
Pawel Morawiecki, Andrii Krutsylo, Maciej Wolczyk, Marek Smieja
Hebbian Continual Representation Learning. CoRR (2022)
Maciej Wolczyk, Karol J. Piczak, Bartosz Wójcik, Lukasz Pustelnik, Pawel Morawiecki, Jacek Tabor, Tomasz Trzcinski, Przemyslaw Spurek
Continual Learning with Guarantees via Weight Interval Constraints. CoRR (2022)
Maciej Wolczyk, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos
Disentangling Transfer in Continual Reinforcement Learning. NeurIPS (2022)
Maciej Wolczyk, Andrii Krutsylo
Remember More by Recalling Less: Investigating the Role of Batch Size in Continual Learning with Experience Replay (Student Abstract). AAAI (2021)
Lukasz Maziarka, Aleksandra Nowak, Maciej Wolczyk, Andrzej Bedychaj
On the relationship between disentanglement and multi-task learning. CoRR (2021)
Oliver Scheel, Luca Bergamini, Maciej Wolczyk, Blazej Osinski, Peter Ondruska
Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients. CoRR (2021)
Marek Smieja, Maciej Wolczyk, Jacek Tabor, Bernhard C. Geiger
SeGMA: Semi-Supervised Gaussian Mixture Autoencoder. IEEE Trans. Neural Networks Learn. Syst. 32 (9) (2021)
Maciej Wolczyk, Bartosz Wójcik, Klaudia Balazy, Igor T. Podolak, Jacek Tabor, Marek Smieja, Tomasz Trzcinski
Zero Time Waste: Recycling Predictions in Early Exit Neural Networks. CoRR (2021)
Matt Vitelli, Yan Chang, Yawei Ye, Maciej Wolczyk, Blazej Osinski, Moritz Niendorf, Hugo Grimmett, Qiangui Huang, Ashesh Jain, Peter Ondruska
SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policies. CoRR (2021)
Maciej Wolczyk, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos
Continual World: A Robotic Benchmark For Continual Reinforcement Learning. NeurIPS (2021)
Maciej Wolczyk, Magdalena Proszewska, Lukasz Maziarka, Maciej Zieba, Patryk Wielopolski, Rafal Kurczab, Marek Smieja
PluGeN: Multi-Label Conditional Generation From Pre-Trained Models. CoRR (2021)
Maciej Wolczyk, Bartosz Wójcik, Klaudia Balazy, Igor T. Podolak, Jacek Tabor, Marek Smieja, Tomasz Trzcinski
Zero Time Waste: Recycling Predictions in Early Exit Neural Networks. NeurIPS (2021)
Maciej Wolczyk, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos
Continual World: A Robotic Benchmark For Continual Reinforcement Learning. CoRR (2021)
Oliver Scheel, Luca Bergamini, Maciej Wolczyk, Blazej Osinski, Peter Ondruska
Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients. CoRL (2021)
Bartosz Wójcik, Maciej Wolczyk, Klaudia Balazy, Jacek Tabor
Finding the Optimal Network Depth in Classification Tasks. ECML/PKDD (3) (2020)
Bartosz Wójcik, Maciej Wolczyk, Klaudia Balazy, Jacek Tabor
Finding the Optimal Network Depth in Classification Tasks. CoRR (2020)
Sylwester Klocek, Lukasz Maziarka, Maciej Wolczyk, Jacek Tabor, Marek Smieja, Jakub Nowak
Multi-task hypernetworks. CoRR (2019)
Marek Smieja, Maciej Wolczyk, Jacek Tabor, Bernhard C. Geiger
SeGMA: Semi-Supervised Gaussian Mixture Auto-Encoder. CoRR (2019)
Maciej Wolczyk, Jacek Tabor, Marek Smieja, Szymon Maszke
Biologically-Inspired Spatial Neural Networks. CoRR (2019)
Sylwester Klocek, Lukasz Maziarka, Maciej Wolczyk, Jacek Tabor, Jakub Nowak, Marek Smieja
Hypernetwork Functional Image Representation. ICANN (Workshop) (2019)