Pawel Wawrzynski

Publication Activity (10 Years)

Years Active: 2004-2024
Publications (10 Years): 33

Top Topics

Recursive Neural Networks

Parameter Tuning

Reinforcement Learning

Top Venues

Publications

Jakub Lyskawa, Pawel Wawrzynski
ACERAC: Efficient Reinforcement Learning in Fine Time Discretization. IEEE Trans. Neural Networks Learn. Syst. 35 (2) (2024)
Radoslaw Nowak, Adam Malkowski, Daniel Cieslak, Piotr Sokól, Pawel Wawrzynski
Graph Vertex Embeddings: Distance, Regularization and Community Detection. ICCS (6) (2024)
Patryk Krukowski, Anna Bielawska, Kamil Ksiazek, Pawel Wawrzynski, Pawel Batorski, Przemyslaw Spurek
HyperInterval: Hypernetwork approach to training weight interval regions in continual learning. CoRR (2024)
Radoslaw Nowak, Adam Malkowski, Daniel Cieslak, Piotr Sokól, Pawel Wawrzynski
Graph Vertex Embeddings: Distance, Regularization and Community Detection. CoRR (2024)
Michal Bortkiewicz, Jakub Lyskawa, Pawel Wawrzynski, Mateusz Ostaszewski, Artur Grudkowski, Bartlomiej Sobieski, Tomasz Trzcinski
Subgoal Reachability in Goal Conditioned Hierarchical Reinforcement Learning. ICAART (1) (2024)
Lukasz Lepak, Pawel Wawrzynski
Reinforcement learning for optimization of energy trading strategy. CoRR (2023)
Lukasz Neumann, Lukasz Lepak, Pawel Wawrzynski
Least Redundant Gated Recurrent Neural Network. IJCNN (2023)
Jakub Lyskawa, Pawel Wawrzynski
Actor-Critic with Variable Time Discretization via Sustained Actions. ICONIP (1) (2023)
Jakub Lyskawa, Pawel Wawrzynski
Actor-Critic with variable time discretization via sustained actions. CoRR (2023)
Adam Malkowski, Jakub Grzechocinski, Pawel Wawrzynski
Graph autoencoder with constant dimensional latent space. CoRR (2022)
Kamil Deja, Pawel Wawrzynski, Wojciech Masarczyk, Daniel Marczak, Tomasz Trzcinski
Multiband VAE: Latent Space Alignment for Knowledge Consolidation in Continual Learning. IJCAI (2022)
Michal Bortkiewicz, Jakub Lyskawa, Pawel Wawrzynski, Mateusz Ostaszewski, Artur Grudkowski, Tomasz Trzcinski
Emergency action termination for immediate reaction in hierarchical reinforcement learning. CoRR (2022)
Adam Malkowski, Jakub Grzechocinski, Pawel Wawrzynski
ReGAE: Graph Autoencoder Based on Recursive Neural Networks. ICONIP (4) (2022)
Wojciech Masarczyk, Pawel Wawrzynski, Daniel Marczak, Kamil Deja, Tomasz Trzcinski
Logarithmic Continual Learning. CoRR (2022)
Grzegorz Rypesc, Lukasz Lepak, Pawel Wawrzynski
Reinforcement Learning for on-line Sequence Transformation. FedCSIS (2022)
Pawel Wawrzynski, Wojciech Masarczyk, Mateusz Ostaszewski
Reinforcement learning with experience replay and adaptation of action dispersion. CoRR (2022)
Wojciech Masarczyk, Pawel Wawrzynski, Daniel Marczak, Kamil Deja, Tomasz Trzcinski
Logarithmic Continual Learning. IEEE Access 10 (2022)
Kamil Deja, Pawel Wawrzynski, Daniel Marczak, Wojciech Masarczyk, Tomasz Trzcinski
Multiband VAE: Latent Space Partitioning for Knowledge Consolidation in Continual Learning. CoRR (2021)
Pawel Wawrzynski, Jakub Lyskawa
ACERAC: Efficient reinforcement learning in fine time discretization. CoRR (2021)
Lukasz Neumann, Pawel Wawrzynski
Deep Memory Update. CoRR (2021)
Kamil Deja, Pawel Wawrzynski, Daniel Marczak, Wojciech Masarczyk, Tomasz Trzcinski
BinPlay: A Binary Latent Autoencoder for Generative Replay Continual Learning. IJCNN (2021)
Grzegorz Rypesc, Lukasz Lepak, Pawel Wawrzynski
Reinforcement Learning for on-line Sequence Transformation. CoRR (2021)
Marcin Szulc, Jakub Lyskawa, Pawel Wawrzynski
A Framework for Reinforcement Learning with Autocorrelated Actions. ICONIP (2) (2020)
Karol Cheinski, Pawel Wawrzynski
DCT-Conv: Coding filters in convolutional networks with Discrete Cosine Transform. CoRR (2020)
Kamil Deja, Pawel Wawrzynski, Daniel Marczak, Wojciech Masarczyk, Tomasz Trzcinski
BinPlay: A Binary Latent Autoencoder for Generative Replay Continual Learning. CoRR (2020)
Marcin Szulc, Jakub Lyskawa, Pawel Wawrzynski
A framework for reinforcement learning with autocorrelated actions. CoRR (2020)
Karol Cheinski, Pawel Wawrzynski
DCT-Conv: Coding filters in convolutional networks with Discrete Cosine Transform. IJCNN (2020)
Pawel Wawrzynski, Pawel Zawistowski, Lukasz Lepak
Automatic hyperparameter tuning in on-line learning: Classic Momentum and ADAM. IJCNN (2020)
Pawel Wawrzynski
Efficient on-line learning with diagonal approximation of loss function Hessian. IJCNN (2019)
Lukasz Neumann, Robert M. Nowak, Rafal Okuniewski, Pawel Wawrzynski
Machine Learning-Based Predictions of Customers' Decisions in Car Insurance. Appl. Artif. Intell. 33 (9) (2019)
Andrea Zanetti, Alberto Testolin, Marco Zorzi, Pawel Wawrzynski
Numerosity Representation in InfoGAN: An Empirical Study. IWANN (2) (2019)
Pawel Wawrzynski
Parameter-Free On-line Deep Learning. AUTOMATION (2017)
Pawel Wawrzynski
ASD+M: Automatic parameter tuning in stochastic optimization and on-line learning. Neural Networks 96 (2017)
Pawel Wawrzynski
Robot's velocity and tilt estimation through computationally efficient fusion of proprioceptive sensors readouts. MMAR (2015)
Pawel Wawrzynski, Jakub Mozaryn, Jan Klimaszewski
Robust estimation of walking robots velocity and tilt using proprioceptive sensors data fusion. Robotics Auton. Syst. 66 (2015)
Michal Majczak, Pawel Wawrzynski
Comparison of two efficient control strategies for two-wheeled balancing robot. MMAR (2015)
Jakub Mozaryn, Jan Klimaszewski, Pawel Kolodziejczyk, Dariusz Swieczkowski-Feiz, Pawel Wawrzynski
Design process and experimental verification of the quadruped robot wave gait. MMAR (2014)
Pawel Wawrzynski
Reinforcement Learning with Experience Replay for Model-Free Humanoid Walking Optimization. Int. J. Humanoid Robotics 11 (3) (2014)
Bartosz Papis, Pawel Wawrzynski
dotRL: A platform for rapid Reinforcement Learning methods development and validation. FedCSIS (2013)
Pawel Wawrzynski, Jakub Mozaryn, Jan Klimaszewski
Robust velocity estimation for legged robot using on-board sensors data fusion. MMAR (2013)
Piotr Suszynski, Pawel Wawrzynski
Learning population of spiking neural networks with perturbation of conductances. IJCNN (2013)
Pawel Wawrzynski
Autonomous Reinforcement Learning with Experience Replay for Humanoid Gait Optimization. INNS-WC (2012)
Pawel Wawrzynski, Bartosz Papis
Fixed point method for autonomous on-line neural network training. Neurocomputing 74 (17) (2011)
Pawel Wawrzynski
Fixed point method of step-size estimation for on-line neural network training. IJCNN (2010)
Pawel Wawrzynski
Real-time reinforcement learning by sequential Actor-Critics and experience replay. Neural Networks 22 (10) (2009)
Pawel Wawrzynski
A Cat-Like Robot Real-Time Learning to Run. ICANNGA (2009)
Pawel Wawrzynski, Jaroslaw Arabas, Pawel Cichosz
Predictive Control for Artificial Intelligence in Computer Games. ICAISC (2008)
Pawel Wawrzynski
Reinforcement Learning in Fine Time Discretization. ICANNGA (1) (2007)
Pawel Wawrzynski, Andrzej Pacut
Reinforcement Learning in Quasi-Continuous Time. CIMCA/IAWTIC (2005)
Pawel Wawrzynski, Andrzej Pacut
Intensive versus Non-intensive Actor-Critic Reinforcement Learning Algorithms. ICAISC (2004)