1 citations · 1 across the 6 of their papers we have counts for
8 papers · 1 filter
Reinforcement learning with experience replay and adaptation of action dispersion
Paweł Wawrzyński, Wojciech Masarczyk, Mateusz Ostaszewski
Effective reinforcement learning requires a proper balance of exploration and exploitation defined by the dispersion of action distribution. However, this balance depends on the ta…
Logarithmic Continual Learning
Wojciech Masarczyk, Paweł Wawrzyński, Daniel Marczak +2
We introduce a neural network architecture that logarithmically reduces the number of self-rehearsal steps in the generative rehearsal of continually learned models. In continual l…
ReGAE: Graph autoencoder based on recursive neural networks
Adam Małkowski, Jakub Grzechociński, Paweł Wawrzyński
Invertible transformation of large graphs into fixed dimensional vectors (embeddings) remains a challenge. Its overcoming would reduce any operation on graphs to an operation in a…
Multiband VAE: Latent Space Alignment for Knowledge Consolidation in Continual Learning
Kamil Deja, Paweł Wawrzyński, Wojciech Masarczyk +2
We propose a new method for unsupervised generative continual learning through realignment of Variational Autoencoder's latent space. Deep generative models suffer from catastrophi…
Reinforcement Learning for on-line Sequence Transformation
Grzegorz Rypeść, Łukasz Lepak, Paweł Wawrzyński
A number of problems in the processing of sound and natural language, as well as in other areas, can be reduced to simultaneously reading an input sequence and writing an output se…
ACERAC: Efficient reinforcement learning in fine time discretization
Jakub Łyskawa, Paweł Wawrzyński
One of the main goals of reinforcement learning (RL) is to provide a~way for physical machines to learn optimal behavior instead of being programmed. However, effective control of…
BinPlay: A Binary Latent Autoencoder for Generative Replay Continual Learning
Kamil Deja, Paweł Wawrzyński, Daniel Marczak +2
We introduce a binary latent space autoencoder architecture to rehearse training samples for the continual learning of neural networks. The ability to extend the knowledge of a mod…
A framework for reinforcement learning with autocorrelated actions
Marcin Szulc, Jakub Łyskawa, Paweł Wawrzyński
The subject of this paper is reinforcement learning. Policies are considered here that produce actions based on states and random elements autocorrelated in subsequent time instant…