Search Results for author:
Found 14 papers, 4 papers with code
Graph Vertex Embeddings: Distance, Regularization and Community Detection
Graph embeddings have emerged as a powerful tool for representing complex network structures in a low-dimensional space, enabling the use of efficient methods that employ the metric structure in the embedding space as a proxy for the topological structure of the data.
Actor-Critic with variable time discretization via sustained actions
Reinforcement learning (RL) methods work in discrete time.
On-line reinforcement learning for optimization of real-life energy trading strategy
In many countries, this balancing is done on the day-ahead (DA) energy markets.
Emergency action termination for immediate reaction in hierarchical reinforcement learning
In this paper, we address this gap in the state-of-the-art approaches and propose a method in which the validity of higher-level actions (thus lower-level goals) is constantly verified at the higher level.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
Reinforcement learning with experience replay and adaptation of action dispersion
To that end, the dispersion should be tuned to assure a sufficiently high probability (densities) of the actions in the replay buffer and the modes of the distributions that generated them, yet this dispersion should not be higher.
ReGAE: Graph autoencoder based on recursive neural networks
In this paper we address the above challenge with recursive neural networks - the encoder and the decoder.
Logarithmic Continual Learning
Our approach leverages allocation of past data in a~set of generative models such that most of them do not require retraining after a~task.
Multiband VAE: Latent Space Alignment for Knowledge Consolidation in Continual Learning
We propose a new method for unsupervised generative continual learning through realignment of Variational Autoencoder's latent space.
Reinforcement Learning for on-line Sequence Transformation
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 sequence of generally different length.
Least Redundant Gated Recurrent Neural Network
It is based on updating the previous memory state with a deep transformation of the lagged state and the network input.
ACERAC: Efficient reinforcement learning in fine time discretization
It is not feasible because it causes the controlled system to jerk, and does not ensure sufficient exploration since a~single action is not long enough to create a~significant experience that could be translated into policy improvement.
BinPlay: A Binary Latent Autoencoder for Generative Replay Continual Learning
We introduce a binary latent space autoencoder architecture to rehearse training samples for the continual learning of neural networks.
A framework for reinforcement learning with autocorrelated actions
Consequently, an agent learns from experiments that are distributed over time and potentially give better clues to policy improvement.
DCT-Conv: Coding filters in convolutional networks with Discrete Cosine Transform
We follow the line of research in which filters of convolutional neural layers are determined on the basis of a smaller number of trained parameters.
